© 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. 1-CLT-HP
    7. 14585
    Prev
    Next
    INDEX
    Explanations

    KA

    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
     Pav
    -0.47
    withOpacity
    -0.46
    sate
    -0.45
     presto
    -0.45
     Ste
    -0.45
    ole
    -0.45
    over
    -0.44
    olar
    -0.44
     Ho
    -0.44
     Th
    -0.44
    POSITIVE LOGITS
     виправивши
    0.80
    PreferredItem
    0.77
    GEBURTSDATUM
    0.77
     Signalez
    0.68
     ་་
    0.67
     betweenstory
    0.65
     Efq
    0.65
    ($__
    0.65
     marinho
    0.65
    InjectAttribute
    0.65
    Activations Density 0.028%

    No Known Activations