© 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. 15189
    Prev
    Next
    INDEX
    Explanations

    question words

    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
    s
    -0.56
    Kjelder
    -0.46
    i
    -0.44
     how
    -0.42
     appuntamento
    -0.42
     wherefore
    -0.41
     cosa
    -0.40
    在她
    -0.39
     المعيارى
    -0.39
    why
    -0.39
    POSITIVE LOGITS
     DOES
    0.88
    EVER
    0.86
     THEY
    0.85
    DOES
    0.84
     MANY
    0.81
     DID
    0.79
     DO
    0.76
     MainAxisSize
    0.75
     they
    0.69
     YOU
    0.68
    Activations Density 0.002%

    No Known Activations