© 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. 44191
    Prev
    Next
    INDEX
    Explanations

    many/close

    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
    ✭✭
    -0.81
    LayoutStyle
    -0.79
    tvguidetime
    -0.77
     snippetHide
    -0.71
    VIAF
    -0.70
    Smarty
    -0.68
    posedge
    -0.67
     propOrder
    -0.66
     InputDecoration
    -0.66
     defaultstate
    -0.66
    POSITIVE LOGITS
    <bos>
    0.79
     to
    0.64
    To
    0.50
    horabuena
    0.50
    orszá
    0.49
    What
    0.48
    a
    0.48
    '
    0.48
     for
    0.47
    Still
    0.46
    Activations Density 0.040%

    No Known Activations