© 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. 5-CLT-HP
    7. 98172
    Prev
    Next
    INDEX
    Explanations

    dividing into groups

    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
    their
    -0.76
     theirs
    -0.73
     незавершена
    -0.71
     članak
    -0.71
    InjectAttribute
    -0.68
     their
    -0.68
    ✨:
    -0.68
    themselves
    -0.67
    principalColumn
    -0.65
    Their
    -0.64
    POSITIVE LOGITS
    stonia
    0.40
     CURIAM
    0.39
     correspond
    0.39
    tito
    0.39
     corresponde
    0.38
    tinyos
    0.38
    bed
    0.38
    spotify
    0.38
     inform
    0.38
     pap
    0.38
    Activations Density 0.012%

    No Known Activations