© 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. 94532
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    kloped
    -0.85
    WebVitals
    -0.84
    ValueGeneration
    -0.80
     Профиль
    -0.75
    LLocation
    -0.73
    ✨:
    -0.73
    }{*}{}
    -0.71
    ContentAlignment
    -0.71
    ритори
    -0.68
    msgTypes
    -0.67
    POSITIVE LOGITS
    I
    0.59
    <bos>
    0.55
     I
    0.54
    G
    0.50
    *
    0.50
    F
    0.50
    <eos>
    0.49
    1
    0.48
    IG
    0.46
    K
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.