© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39802
    Prev
    Next
    INDEX
    Explanations

    commentary

    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
     comment
    -1.95
     comments
    -1.92
     commentary
    -1.79
    comment
    -1.76
     commentaries
    -1.63
    comments
    -1.59
     commenting
    -1.59
     commented
    -1.55
     Comment
    -1.53
     comentarios
    -1.51
    POSITIVE LOGITS
     about
    0.70
     on
    0.56
     متعلقه
    0.48
     based
    0.47
     delivered
    0.46
     ***!
    0.44
     from
    0.43
     Abou
    0.43
     دریافت‌شده
    0.42
     backed
    0.42
    Activations Density 0.235%

    No Known Activations