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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92143
    Prev
    Next
    INDEX
    Explanations

    best

    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
     and
    -0.57
    LLYWOOD
    -0.42
    ,
    -0.40
    </h2>
    -0.39
     &
    -0.39
    MathML
    -0.39
     och
    -0.36
    </u>
    -0.36
    Motorola
    -0.36
     armado
    -0.35
    POSITIVE LOGITS
    findpost
    0.91
     بيها
    0.86
    featureID
    0.86
     ModelExpression
    0.84
    ValueGeneration
    0.82
    DockStyle
    0.81
     nakalista
    0.80
    LookAnd
    0.79
     متعلقه
    0.79
    ReusableCell
    0.76
    Activations Density 0.005%

    No Known Activations