© 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. 1-CLT-HP
    7. 12972
    Prev
    Next
    INDEX
    Explanations

    term

    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
     sẻ
    -0.65
     doInBackground
    -0.60
    WriteLiteral
    -0.58
     referrerpolicy
    -0.57
    الحياه
    -0.56
    >{@
    -0.55
    GraphicsUnit
    -0.54
     resourceCulture
    -0.54
    ]-->
    -0.53
    ])){
    -0.52
    POSITIVE LOGITS
    ographers
    0.68
    Statistiche
    0.56
    istics
    0.55
    ographer
    0.54
    anasia
    0.54
     therapists
    0.52
     mathematicians
    0.52
     observers
    0.50
    ologists
    0.50
    istici
    0.49
    Activations Density 0.016%

    No Known Activations