© 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. 1-CLT-HP
    4. 12953
    Prev
    Next
    INDEX
    Explanations

    minutes

    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
    Parcelize
    -0.75
    ViewFeatures
    -0.59
    quoi
    -0.58
    κης
    -0.58
     }{@
    -0.58
     kaarangay
    -0.57
     minutes
    -0.57
    bkz
    -0.55
    devamını
    -0.53
     vPvB
    -0.53
    POSITIVE LOGITS
     يتيمه
    0.69
    <bos>
    0.64
    -
    0.55
    Personendaten
    0.53
     Infórmanos
    0.46
    MLLoader
    0.45
     tops
    0.45
    day
    0.44
    पया
    0.43
    ays
    0.43
    Activations Density 0.021%

    No Known Activations