© 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. 4-CLT-HP
    7. 2671
    Prev
    Next
    INDEX
    Explanations

    Actions and events

    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
     autorytatywna
    -0.98
     <<<<<<<<<<<<<<
    -0.93
     дописавши
    -0.84
    ConstraintMaker
    -0.81
    !!</
    -0.79
    !',
    -0.77
    发表于
    -0.73
    Portale
    -0.73
    ModelSerializer
    -0.71
    .[/
    -0.71
    POSITIVE LOGITS
     this
    0.73
    this
    0.67
     denna
    0.46
     derni
    0.43
     entière
    0.43
     déchir
    0.42
     domenica
    0.42
     espont
    0.41
     agricoles
    0.41
     Thursday
    0.40
    Activations Density 0.003%

    No Known Activations