© 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. 4-CLT-HP
    7. 810
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ụy
    -0.60
     صوتيه
    -0.58
     sanitaires
    -0.54
     समीक्षाओं
    -0.52
     Exacts
    -0.51
     AppCompatTheme
    -0.50
     Paro
    -0.50
    adpleegd
    -0.49
    pherals
    -0.49
    enment
    -0.48
    POSITIVE LOGITS
     selection
    0.67
     wide
    0.66
     few
    0.63
     significant
    0.60
     total
    0.59
    ramid
    0.59
     great
    0.58
     quantity
    0.56
     considerable
    0.55
    StructEnd
    0.54
    Activations Density 0.002%

    No Known Activations