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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 414
    Prev
    Next
    INDEX
    Explanations

    the

    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
     незавершена
    -0.73
     مشين
    -0.72
    IntoConstraints
    -0.69
     telefónica
    -0.66
    Geplaatst
    -0.59
    Portail
    -0.59
     hâte
    -0.57
    isContained
    -0.56
    migrationBuilder
    -0.56
    ResumeLayout
    -0.56
    POSITIVE LOGITS
     inter
    0.57
     off
    0.54
     censiti
    0.50
     invested
    0.50
     thrown
    0.49
    ))).
    0.49
    ...).
    0.48
    уна
    0.48
    …).
    0.48
    +)$
    0.48
    Activations Density 0.015%

    No Known Activations