© 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. 14457
    Prev
    Next
    INDEX
    Explanations

    medium

    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
     Medium
    -1.09
    medium
    -1.06
    Medium
    -1.02
     medium
    -1.00
     MEDIUM
    -0.91
    MEDIUM
    -0.77
    migrationBuilder
    -0.76
     médias
    -0.73
     mediano
    -0.71
     <=",
    -0.69
    POSITIVE LOGITS
     grades
    0.48
    some
    0.47
     lengths
    0.47
     genotypes
    0.45
     doses
    0.44
     frames
    0.43
     guns
    0.43
     lounges
    0.42
     quantities
    0.41
     sauces
    0.40
    Activations Density 0.098%

    No Known Activations