© 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. 1-CLT-HP
    7. 16240
    Prev
    Next
    INDEX
    Explanations

    release

    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
     Release
    -1.16
     release
    -1.14
     releases
    -1.03
    release
    -1.02
     Released
    -0.98
     RELEASE
    -0.94
    releases
    -0.93
     released
    -0.93
    Release
    -0.91
    released
    -0.91
    POSITIVE LOGITS
     from
    0.86
    from
    0.56
    fromnode
    0.52
    esteld
    0.50
    From
    0.49
     aus
    0.47
     From
    0.47
    προ
    0.47
     marching
    0.47
    HandlerContext
    0.47
    Activations Density 0.033%

    No Known Activations