© 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. 43440
    Prev
    Next
    INDEX
    Explanations

    fear

    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
     Efq
    -0.90
     whoſe
    -0.81
     itſelf
    -0.81
     myſelf
    -0.78
     noires
    -0.73
     himſelf
    -0.69
     imprimée
    -0.69
     ſhe
    -0.69
     débat
    -0.69
     fermés
    -0.68
    POSITIVE LOGITS
    ly
    1.18
    less
    0.94
    able
    0.84
    ous
    0.66
    man
    0.66
    ful
    0.66
    lable
    0.64
    ler
    0.64
    ish
    0.60
    line
    0.59
    Activations Density 0.710%

    No Known Activations