© 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. 5-CLT-HP
    7. 6040
    Prev
    Next
    INDEX
    Explanations

    Numerical ranges and limits

    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
     كومونز
    -0.71
     ſind
    -0.67
     Referential
    -0.66
     gata
    -0.65
     faſt
    -0.65
     barbati
    -0.65
     Urbano
    -0.64
    aderas
    -0.64
     ainfi
    -0.64
     widows
    -0.63
    POSITIVE LOGITS
    rungsseite
    0.44
     Paglinawan
    0.42
    WireFormatLite
    0.42
    SizeF
    0.40
    ówn
    0.39
     '{@
    0.38
    تقاوى
    0.37
    WireFormat
    0.35
    ppelin
    0.35
    ApiModelProperty
    0.35
    Activations Density 0.003%

    No Known Activations