© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Roskov
    -0.79
    AsUp
    -0.66
    OGND
    -0.62
    #+#
    -0.62
     VIAF
    -0.61
    StructEnd
    -0.60
    PreferredItem
    -0.60
    TagMode
    -0.59
    InstanceState
    -0.58
    principalColumn
    -0.57
    POSITIVE LOGITS
     sheet
    0.61
    +");
    0.59
     SHEET
    0.57
     possible
    0.56
     sheets
    0.56
    .$.
    0.54
     Possible
    0.54
     ber
    0.53
    пис
    0.53
    )}$
    0.52
    Activations Density 0.015%

    No Known Activations