© 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. 5-CLT-HP
    7. 1010
    Prev
    Next
    INDEX
    Explanations

    the

    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>
    -0.87
    Nazionale
    -0.59
     doInBackground
    -0.54
    iencing
    -0.51
    having
    -0.50
     having
    -0.48
     betweenstory
    -0.47
     был
    -0.47
    ########.
    -0.46
    DeleteBehavior
    -0.46
    POSITIVE LOGITS
     will
    0.72
     NSCoder
    0.63
    addPreferredGap
    0.63
     won
    0.60
    will
    0.59
    asem
    0.56
     WILL
    0.55
    стюм
    0.54
    ussis
    0.54
    الإنجليزية
    0.53
    Activations Density 0.003%

    No Known Activations