© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    import

    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
     Theſe
    -0.76
    ſelf
    -0.74
     houſe
    -0.69
     pleaſure
    -0.67
    ſelves
    -0.67
     Houſe
    -0.64
     purpoſe
    -0.64
     myſelf
    -0.63
     Efq
    -0.62
     Diſ
    -0.61
    POSITIVE LOGITS
     ModelExpression
    0.67
    AsUp
    0.62
    PhysRev
    0.59
     Bourgoin
    0.58
    NgModule
    0.58
    enumi
    0.58
    AutoField
    0.58
    lgari
    0.58
     TextAppearance
    0.56
    RunWith
    0.56
    Activations Density 0.014%

    No Known Activations