© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41529
    Prev
    Next
    INDEX
    Explanations

    events and activities

    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
     activities
    -0.69
    SourceChecksum
    -0.68
    rinus
    -0.58
    انيف
    -0.58
    activities
    -0.58
     Activities
    -0.56
    ynchronously
    -0.56
    ourne
    -0.55
    jaman
    -0.55
     Projects
    -0.54
    POSITIVE LOGITS
    <bos>
    0.74
    __':
    0.64
    Demografia
    0.55
    '}>
    0.54
     Shakspeare
    0.52
    __':
    0.50
    AutoScaleMode
    0.50
    ázaro
    0.49
    MENAFN
    0.47
    __":
    0.47
    Activations Density 0.082%

    No Known Activations