© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    search

    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
     ModelExpression
    -0.58
    Recherche
    -0.49
     محفوظة
    -0.47
     مرئيه
    -0.46
     reticulum
    -0.45
     AssemblyCompany
    -0.44
    search
    -0.43
     intramuscular
    -0.43
     ISTAT
    -0.42
     Catawiki
    -0.42
    POSITIVE LOGITS
    Politik
    0.66
    OnAdd
    0.60
    .*")]
    0.60
     pouss
    0.58
    BeNil
    0.56
    icali
    0.56
     BoxFit
    0.55
     GetEnumerator
    0.54
     Wicidata
    0.53
    ?,?,
    0.53
    Activations Density 0.054%

    No Known Activations