© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    Faux or names

    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
    apura
    -0.44
    antren
    -0.43
     Tap
    -0.41
    tap
    -0.41
     Dan
    -0.41
    agram
    -0.40
    Sport
    -0.39
    g
    -0.39
     Sport
    -0.39
    rum
    -0.39
    POSITIVE LOGITS
    Personensuche
    1.02
    GEBURTSDATUM
    0.86
    parsedMessage
    0.80
     للاسماء
    0.77
    出版年
    0.75
    expandindo
    0.73
     propOrder
    0.72
     purpoſe
    0.72
     Efq
    0.71
     doInBackground
    0.71
    Activations Density 0.002%

    No Known Activations