© 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. 42731
    Prev
    Next
    INDEX
    Explanations

    dup

    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
     itſelf
    -0.80
     Shakspeare
    -0.69
     Cæsar
    -0.68
     Efq
    -0.66
     Universitaria
    -0.66
     Dijo
    -0.64
     myſelf
    -0.63
     alone
    -0.61
     Allí
    -0.60
     yourselves
    -0.60
    POSITIVE LOGITS
    Hentet
    0.84
    Autoritní
    0.73
    OGND
    0.72
     gynhyrchwyd
    0.66
    "):
    0.64
    ">//
    0.63
    lccn
    0.63
    ielo
    0.62
    ñoz
    0.62
    XmlAccessorType
    0.61
    Activations Density 0.109%

    No Known Activations