© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12042
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to Java programming and development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1127
    +0.14
    0.5%
    168
    +0.12
    0.4%
    1837
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.14
    0.03
    1511
    +0.12
    0.01
    876
    +0.09
    -0.00
    Negative Logits
     bill
    -0.52
    borderTop
    -0.51
    DatabaseError
    -0.51
    дото
    -0.50
    ‏‏
    -0.48
    כי
    -0.48
     inmig
    -0.47
    randint
    -0.47
    Fprintf
    -0.47
    켰
    -0.46
    POSITIVE LOGITS
     suscep
    1.26
     emphat
    1.24
     desir
    1.17
     inext
    1.17
     JAVA
    1.13
     ?...
    1.13
     inconce
    1.12
     compen
    1.11
     [''
    1.11
     ardu
    1.10
    Activations Density 0.151%

    No Known Activations