© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2156
    Prev
    Next
    INDEX
    Explanations

    mentions of "tank" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    1.3%
    228
    +0.13
    0.8%
    755
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.21
    0.02
    1376
    +0.13
    0.02
    1520
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.44
     disbur
    -0.64
     assimilate
    -0.63
     endeavored
    -0.61
     endow
    -0.61
     overcrow
    -0.60
    
    -0.59
     shivered
    -0.58
     endeavoured
    -0.57
     shuddered
    -0.56
    POSITIVE LOGITS
     tank
    1.38
     Tank
    1.32
     tanks
    1.32
    Tank
    1.30
     Tanks
    1.26
    Tanks
    1.21
    tank
    1.20
     TANK
    1.18
    TANK
    1.15
    tanks
    1.07
    Activations Density 0.035%

    No Known Activations