© 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. 0-CLT-HP
    7. 95445
    Prev
    Next
    INDEX
    Explanations

    DVD

    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
    tern
    -0.60
    Filmo
    -0.53
    fn
    -0.52
    iroz
    -0.51
    thur
    -0.50
    vaz
    -0.49
    runner
    -0.47
     regula
    -0.47
     tro
    -0.46
    ruff
    -0.43
    POSITIVE LOGITS
     Efq
    1.01
     Monfieur
    0.96
     itſelf
    0.94
    '},
    0.91
     myſelf
    0.85
     Chriftian
    0.82
     Jefus
    0.82
     Theſe
    0.79
     Anſ
    0.77
     pleaſure
    0.77
    Activations Density 0.149%

    No Known Activations