© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 873
    Prev
    Next
    INDEX
    Explanations

    outs

    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
    outs
    -1.36
     Outs
    -1.07
     outs
    -1.06
    Outs
    -1.03
    ValueStyle
    -0.68
    RuleContext
    -0.68
    SetOutput
    -0.65
    OUT
    -0.65
    Personensuche
    -0.63
     חיצוניים
    -0.63
    POSITIVE LOGITS
    iecie
    0.48
    igné
    0.45
    res
    0.44
     bearer
    0.43
    rith
    0.42
    arians
    0.42
    >[]
    0.42
    SerializedSize
    0.41
    THON
    0.41
    wix
    0.41
    Activations Density 0.024%

    No Known Activations