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

    Neuronpedia

    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. 0-RES-JB
    11. 235
    Prev
    Next
    INDEX
    Explanations

    phrases related to sucking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1757
    +0.09
    0.3%
    1921
    +0.07
    0.2%
    1047
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.09
    0.02
    1836
    +0.07
    0.02
    1638
    +0.07
    0.02
    Negative Logits
    /***
    -0.59
     tortas
    -0.59
     pican
    -0.56
     telur
    -0.54
    żdy
    -0.53
    Fuckin
    -0.52
    iniums
    -0.51
    Địa
    -0.51
    habited
    -0.50
     mostaza
    -0.49
    POSITIVE LOGITS
     suck
    2.81
     sucked
    2.26
     sucking
    2.15
     sucks
    2.13
     Suck
    2.13
    suck
    2.06
    Suck
    1.80
     suckers
    1.26
     sucker
    1.20
     stinks
    1.14
    Activations Density 0.123%

    No Known Activations