© 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. 2033
    Prev
    Next
    INDEX
    Explanations

    with

    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
     HttpNotFound
    -0.64
     ContentValues
    -0.60
    UrlResolution
    -0.60
     saites
    -0.59
    Demografie
    -0.57
     resourceCulture
    -0.56
     ffilmiau
    -0.56
    Zunanje
    -0.55
    MessageOf
    -0.54
     initComponents
    -0.53
    POSITIVE LOGITS
     respect
    1.02
     changes
    0.76
     respects
    0.75
     Respect
    0.66
    respect
    0.64
     différences
    0.64
     change
    0.63
     regard
    0.62
     changement
    0.61
     changing
    0.60
    Activations Density 0.002%

    No Known Activations