© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42391
    Prev
    Next
    INDEX
    Explanations

    that

    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
     Efq
    -1.00
    GEBURTSDATUM
    -0.82
    Aktualisiert
    -0.80
     ſind
    -0.79
    FieldBuilder
    -0.77
     Eſ
    -0.77
     تضيفلها
    -0.77
     ―――――
    -0.77
     auffi
    -0.74
     doubtnut
    -0.74
    POSITIVE LOGITS
     is
    1.10
    ’
    1.03
    '
    0.99
     makes
    0.90
     can
    0.81
     might
    0.78
     may
    0.75
     doesn
    0.74
     isn
    0.71
     has
    0.70
    Activations Density 0.049%

    No Known Activations