© 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. 20-CLT-HP
    7. 72733
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · 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
    /***/
    -0.57
    sel
    -0.53
    migrationBuilder
    -0.44
    исленность
    -0.40
    sels
    -0.38
    روابط
    -0.38
     recevrez
    -0.36
    らく
    -0.36
    marginVertical
    -0.35
     EdgeInsets
    -0.35
    POSITIVE LOGITS
     right
    2.20
     correct
    1.77
    right
    1.76
    Right
    1.65
     Right
    1.59
    correct
    1.55
     RIGHT
    1.49
    RIGHT
    1.46
    Correct
    1.40
     Correct
    1.39
    Activations Density 0.009%

    No Known Activations