© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
     Всё
    -0.64
    colour
    -0.61
     colour
    -0.60
    Ещё
    -0.59
     customised
    -0.59
    ёх
    -0.59
    Colour
    -0.57
     authorised
    -0.56
    ёв
    -0.56
     centre
    -0.55
    POSITIVE LOGITS
    EDEFAULT
    0.68
    ByVersion
    0.62
     Audiodateien
    0.61
    Rohy
    0.59
     Meksiku
    0.59
    SBATCH
    0.58
     Italijani
    0.56
    ioli
    0.55
    principalTable
    0.54
    ModelSerializer
    0.54
    Activations Density 0.006%

    No Known Activations