© 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. 0-CLT-HP
    7. 92128
    Prev
    Next
    INDEX
    Explanations

    lows

    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
    DoubleQuotes
    -0.63
    érience
    -0.59
    WebControls
    -0.59
     pétrole
    -0.59
     loisirs
    -0.58
     recev
    -0.58
    RectangleBorder
    -0.57
    DockStyle
    -0.57
     mérit
    -0.56
     autorytatywna
    -0.56
    POSITIVE LOGITS
    oldt
    0.57
    ers
    0.54
    eabouts
    0.53
    quartered
    0.52
    s
    0.52
     bug
    0.50
    ities
    0.50
    ativity
    0.50
    ashe
    0.49
    getInteger
    0.48
    Activations Density 0.025%

    No Known Activations