© 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. 4-CLT-HP
    7. 4598
    Prev
    Next
    INDEX
    Explanations

    Numbers and measurements

    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
     MainAxisSize
    -0.94
     فريبيس
    -0.85
    WebVitals
    -0.81
    enterOuterAlt
    -0.79
    MLLoader
    -0.73
    InSection
    -0.73
    IsMutable
    -0.72
     avoient
    -0.72
     الرياضيه
    -0.71
    XmlAccessType
    -0.71
    POSITIVE LOGITS
    -
    0.59
    <bos>
    0.58
     –
    0.50
    virt
    0.46
     $-$
    0.46
    –
    0.46
     parts
    0.46
     -
    0.45
     instead
    0.43
    --
    0.41
    Activations Density 0.015%

    No Known Activations