© 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. 43054
    Prev
    Next
    INDEX
    Explanations

    rampant

    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
     Codes
    -0.84
    ika
    -0.80
    ka
    -0.75
    IKA
    -0.74
     codes
    -0.73
     CODES
    -0.68
     rod
    -0.67
     Code
    -0.66
     códigos
    -0.65
     code
    -0.64
    POSITIVE LOGITS
     Anſ
    0.87
     itſelf
    0.83
     Majefty
    0.81
     Reſ
    0.80
     Monfieur
    0.77
     myſelf
    0.75
     raiſ
    0.74
     Jefus
    0.73
     ſche
    0.73
     ―――――
    0.72
    Activations Density 1.531%

    No Known Activations