© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43684
    Prev
    Next
    INDEX
    Explanations

    Kat

    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
     Kat
    -0.85
    Kat
    -0.73
     initComponents
    -0.69
     stool
    -0.60
     kat
    -0.60
    esserung
    -0.59
     Cæsar
    -0.57
    Tikang
    -0.56
     propOrder
    -0.55
     fair
    -0.55
    POSITIVE LOGITS
     useParams
    0.56
    currentColor
    0.52
    posób
    0.49
    RenderAtEndOf
    0.48
    جوايز
    0.48
    hemiah
    0.46
    Хьажоргаш
    0.46
    hadiran
    0.46
    hexyl
    0.46
    ApiModelProperty
    0.44
    Activations Density 0.057%

    No Known Activations