© 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. 91042
    Prev
    Next
    INDEX
    Explanations

    between

    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
    Negative Logits
    ]();
    -0.60
     Theſe
    -0.59
     ſmall
    -0.59
    didReceive
    -0.57
    ureusement
    -0.57
    '):
    -0.52
     détru
    -0.52
     biar
    -0.52
     فريبيس
    -0.52
    %",
    -0.51
    POSITIVE LOGITS
    .
    0.57
    MLLoader
    0.52
    verwijspagina
    0.52
    fetchone
    0.50
    AdapterFactory
    0.49
    BagLayout
    0.49
    ,
    0.49
    simult
    0.48
    pushFollow
    0.48
    aternion
    0.48
    Activations Density 0.021%

    No Known Activations