© 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. 44138
    Prev
    Next
    INDEX
    Explanations

    economics

    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
    //
    -0.58
    ISupport
    -0.54
     Eurasian
    -0.54
    ates
    -0.54
     cava
    -0.52
    urlopen
    -0.51
    CA
    -0.51
     Vive
    -0.50
    çants
    -0.50
    essen
    -0.50
    POSITIVE LOGITS
     of
    0.61
    uiente
    0.57
    ientôt
    0.57
    الحياه
    0.55
     fieldNum
    0.55
    rawDesc
    0.55
    quième
    0.54
    toolStripButton
    0.54
    addCriterion
    0.52
    <bos>
    0.51
    Activations Density 0.162%

    No Known Activations