© 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. 5-CLT-HP
    7. 105
    Prev
    Next
    INDEX
    Explanations

    official statements/releases

    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
     lắm
    -0.47
    ="@+
    -0.46
    )_/¯
    -0.44
     seedlings
    -0.43
    zake
    -0.43
     leksikon
    -0.42
    <bos>
    -0.42
     quim
    -0.42
     mystère
    -0.41
     signs
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.73
    abestanden
    0.67
    évaluateur
    0.64
    featureID
    0.63
     فريبيس
    0.63
     informée
    0.60
     ProtoMessage
    0.59
    UseVisualStyle
    0.58
    WebVitals
    0.58
     وتسجيلات
    0.58
    Activations Density 0.001%

    No Known Activations