© 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. 5629
    Prev
    Next
    INDEX
    Explanations

    by

    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
    -0.56
    SystemColors
    -0.55
    labelControl
    -0.52
    AndEndTag
    -0.52
    مصادر
    -0.51
    endpush
    -0.48
    copo
    -0.48
     Traduction
    -0.48
    BuildContext
    -0.47
    </thead>
    -0.47
    POSITIVE LOGITS
     OnTriggerEnter
    0.64
     disambiguazione
    0.59
    "]();
    0.57
     rendus
    0.55
    PreferredItem
    0.55
    новништво
    0.52
     Sarko
    0.50
     firstly
    0.50
    ыгана
    0.50
    featureID
    0.49
    Activations Density 0.006%

    No Known Activations