© 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. Gemma-2-2B
    5. 4-CLT-HP
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    Turn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.69
    таратура
    -0.62
     FileReader
    -0.59
     convertView
    -0.58
    __':
    -0.57
    yntaxException
    -0.55
    oustics
    -0.54
    writeFieldEnd
    -0.53
     AssemblyCulture
    -0.51
    chism
    -0.51
    POSITIVE LOGITS
    IMPORTED
    0.56
    permanent
    0.55
    PERM
    0.53
    flip
    0.52
    InjectAttribute
    0.52
    awake
    0.51
    Permanent
    0.51
     permanent
    0.49
     birth
    0.49
    Flip
    0.49
    Activations Density 0.001%

    No Known Activations