© 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. 72822
    Prev
    Next
    INDEX
    Explanations

    2

    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
    enterOuterAlt
    -0.68
    LEncoder
    -0.67
    };*/
    -0.63
     WaitForSeconds
    -0.59
    UnknownFields
    -0.57
    glGen
    -0.57
    reuung
    -0.56
     Himmel
    -0.56
    NOPQRST
    -0.56
    AxisAlignment
    -0.55
    POSITIVE LOGITS
    gore
    0.54
    Халык
    0.46
    openzeppelin
    0.46
     VIDEOTAPE
    0.43
     Shy
    0.41
    จัง
    0.41
    encodeWith
    0.41
    ch
    0.40
    WriteAttribute
    0.40
    拙
    0.39
    Activations Density 0.003%

    No Known Activations