© 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. 0-CLT-HP
    7. 42531
    Prev
    Next
    INDEX
    Explanations

    share

    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
     rire
    -0.56
    urement
    -0.54
    extAlignment
    -0.54
     agradec
    -0.53
     Partagez
    -0.51
    antaranya
    -0.50
    ClientRect
    -0.49
     Elmer
    -0.48
    DLE
    -0.48
     Share
    -0.47
    POSITIVE LOGITS
     CanadaChoose
    0.65
    principalTable
    0.63
    IsUnicode
    0.59
    ngua
    0.57
     overlaps
    0.57
    NameInMap
    0.56
     Bioaccumulative
    0.56
    timewa
    0.56
    complexContent
    0.55
    \{\\
    0.54
    Activations Density 0.076%

    No Known Activations