© 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. 91141
    Prev
    Next
    INDEX
    Explanations

    tissue

    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
     and
    -0.53
    .
    -0.52
     that
    -0.48
     global
    -0.42
     right
    -0.40
     North
    -0.40
    ,
    -0.40
     Sub
    -0.39
     from
    -0.39
     —
    -0.39
    POSITIVE LOGITS
     ivelany
    1.02
     bezeichneter
    0.97
    __":
    0.93
    InjectAttribute
    0.84
    RenderAtEndOf
    0.84
    /).
    0.82
    abestanden
    0.82
    findpost
    0.81
    UrlResolution
    0.81
    SharedCtor
    0.80
    Activations Density 0.048%

    No Known Activations