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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 443
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Katona"

    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
    31
    +0.08
    0.2%
    1145
    +0.08
    0.2%
    196
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.05
    1363
    +0.08
    0.03
    283
    +0.07
    0.01
    Negative Logits
     remplace
    -0.57
    ilingual
    -0.51
     pageNo
    -0.51
    terraform
    -0.51
     contribue
    -0.50
     tė
    -0.48
    ↦
    -0.47
    Normdaten
    -0.46
     ویکی‌پدی
    -0.46
    otheby
    -0.46
    POSITIVE LOGITS
    ona
    1.08
    TM
    0.91
     TM
    0.87
    ONA
    0.86
     intercepts
    0.78
     intercept
    0.75
    estrel
    0.68
     Moslem
    0.68
     interceptor
    0.66
     tm
    0.65
    Activations Density 0.316%

    No Known Activations