© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    making

    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
     purpoſe
    -1.14
     reaſon
    -1.05
     houſe
    -1.05
    InjectAttribute
    -1.05
    OGND
    -1.02
     leaſt
    -1.00
     ſmall
    -1.00
     Мексичка
    -0.99
     cauſe
    -0.99
    endphp
    -0.97
    POSITIVE LOGITS
     in
    0.54
    ual
    0.51
    ary
    0.50
    .
    0.48
    :
    0.47
     is
    0.47
    ;
    0.47
     by
    0.46
     (
    0.45
     with
    0.45
    Activations Density 0.208%

    No Known Activations