© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93047
    Prev
    Next
    INDEX
    Explanations

    rights

    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
     AssemblyCulture
    -0.83
    #+#
    -0.67
    idł
    -0.63
    aarrggbb
    -0.61
     blessés
    -0.61
    ControllerAdvice
    -0.61
    bbene
    -0.61
     démission
    -0.60
    dafx
    -0.59
     déchir
    -0.58
    POSITIVE LOGITS
     to
    0.55
    ————————————————
    0.54
    decorate
    0.53
     Codable
    0.51
     proportion
    0.50
    FormsModule
    0.50
    áng
    0.50
    ful
    0.49
     sik
    0.49
     
    0.49
    Activations Density 0.052%

    No Known Activations