© 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. 94044
    Prev
    Next
    INDEX
    Explanations

    facet

    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
    rungsseite
    -0.92
     blessés
    -0.88
     typelib
    -0.88
     prisonniers
    -0.87
     chrétiens
    -0.87
     Fiber
    -0.84
     feroit
    -0.82
     pö
    -0.79
    extAlignment
    -0.78
    Fiber
    -0.77
    POSITIVE LOGITS
    ing
    0.96
    able
    0.83
    ed
    0.82
    ability
    0.65
    ian
    0.64
     for
    0.59
    ings
    0.59
    age
    0.59
    ary
    0.59
    -
    0.59
    Activations Density 0.097%

    No Known Activations