© 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. 93704
    Prev
    Next
    INDEX
    Explanations

    Quality

    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
    expandindo
    -0.99
     مشين
    -0.91
    AndEndTag
    -0.83
    GEBURTSDATUM
    -0.82
    quality
    -0.82
     onPostExecute
    -0.81
    Vidite
    -0.80
     ſche
    -0.80
    :✨
    -0.79
     Efq
    -0.77
    POSITIVE LOGITS
     épaules
    0.51
    ,
    0.45
     urusan
    0.45
    Suspense
    0.43
    removeAttr
    0.42
    getContentPane
    0.42
     péri
    0.41
     using
    0.40
    IMPORTED
    0.39
     gants
    0.39
    Activations Density 0.030%

    No Known Activations