© 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. 5982
    Prev
    Next
    INDEX
    Explanations

    math/code problems

    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
    ########.
    -0.67
     ModelExpression
    -0.64
    +#+#
    -0.57
    webElementGuid
    -0.57
     AssemblyCulture
    -0.54
    发表于
    -0.50
     FIA
    -0.47
    WebElementEntity
    -0.47
     affirmative
    -0.47
    rítica
    -0.47
    POSITIVE LOGITS
    InstanceState
    0.58
     nommé
    0.52
    ElementException
    0.50
    penny
    0.49
    Shawn
    0.49
     nommée
    0.49
     matière
    0.48
    :=\
    0.48
    tivité
    0.48
    kaner
    0.48
    Activations Density 0.000%

    No Known Activations