© 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. 15959
    Prev
    Next
    INDEX
    Explanations

    text

    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
     text
    -1.10
    Text
    -1.05
     Text
    -1.03
    text
    -1.00
    ########.
    -0.98
     texts
    -0.91
     textual
    -0.85
    TEXT
    -0.81
     Texts
    -0.79
     texte
    -0.78
    POSITIVE LOGITS
    interopRequire
    0.48
    </tfoot>
    0.45
    DeleteBehavior
    0.44
    SAMPLES
    0.43
    nuovo
    0.41
    ombe
    0.41
     POSTS
    0.40
    yses
    0.40
    ERSON
    0.40
     Trent
    0.39
    Activations Density 0.012%

    No Known Activations