© 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. 2136
    Prev
    Next
    INDEX
    Explanations

    evaluate

    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
    OutputType
    -0.49
     سرا
    -0.49
     richten
    -0.48
    UpdatedAt
    -0.46
    upassen
    -0.44
    multicolumn
    -0.44
     laiko
    -0.43
     setName
    -0.42
    ungszeit
    -0.42
    heten
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.91
     surla
    0.79
    tagHelperRunner
    0.75
    ⓧ
    0.71
    UserScript
    0.71
     ModelExpression
    0.65
    __":
    0.65
    Obrázky
    0.64
     Meksiku
    0.64
    ContentAsync
    0.63
    Activations Density 0.013%

    No Known Activations