© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92325
    Prev
    Next
    INDEX
    Explanations

    does

    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
     HasFactory
    -0.79
    Personensuche
    -0.73
    Did
    -0.71
    EndInit
    -0.70
    ostante
    -0.70
     InputDecoration
    -0.68
     did
    -0.66
    did
    -0.66
    ftagPool
    -0.65
    RenderAtEndOf
    -0.65
    POSITIVE LOGITS
     not
    1.03
     so
    0.89
     NOT
    0.79
     make
    0.70
     have
    0.65
     identify
    0.65
     get
    0.65
    not
    0.63
     find
    0.63
     offer
    0.61
    Activations Density 0.120%

    No Known Activations