Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 913
    Prev
    Next
    INDEX
    Explanations

    born

    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
    UIControlState
    -0.57
    gonic
    -0.55
     if
    -0.54
    antMatchers
    -0.53
    fated
    -0.51
     Ejecutivo
    -0.51
     gerichtet
    -0.51
    astify
    -0.51
     privados
    -0.50
     <=",
    -0.50
    POSITIVE LOGITS
     estekak
    0.66
    endphp
    0.56
     Misty
    0.53
    BagLayout
    0.53
    able
    0.53
    addPreferredGap
    0.53
     purpoſe
    0.52
    <bos>
    0.51
    agin
    0.51
     Cuth
    0.50
    Activations Density 0.120%

    No Known Activations