© 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. 0-CLT-HP
    7. 95372
    Prev
    Next
    INDEX
    Explanations

    vised

    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
    StoryboardSegue
    -0.72
    rxjs
    -0.69
    AddHtmlAttribute
    -0.69
     Palae
    -0.62
    Personensuche
    -0.59
     esboço
    -0.59
     referenties
    -0.58
    unknownFields
    -0.58
     blushing
    -0.58
     onCancelled
    -0.57
    POSITIVE LOGITS
    lammatory
    0.56
    ced
    0.55
     way
    0.54
    INGEN
    0.52
    ci
    0.52
    cing
    0.51
    inya
    0.51
    volved
    0.51
    tanleria
    0.50
    volving
    0.50
    Activations Density 0.443%

    No Known Activations