© 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. 5-CLT-HP
    7. 92804
    Prev
    Next
    INDEX
    Explanations

    idium

    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
    -0.93
    (!__
    -0.76
    NUMX
    -0.72
     <<<<<<<<<<<<<<
    -0.72
    rungsseite
    -0.71
     الحره
    -0.70
    ThroughAttribute
    -0.70
     мәкал
    -0.69
    AndEndTag
    -0.68
    twimg
    -0.67
    POSITIVE LOGITS
    as
    0.56
    d
    0.50
    at
    0.49
    in
    0.47
    a
    0.45
    an
    0.45
    to
    0.42
    te
    0.41
    Stack
    0.40
     Towne
    0.40
    Activations Density 0.001%

    No Known Activations