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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39919
    Prev
    Next
    INDEX
    Explanations

    thousand

    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
     threat
    -0.57
     to
    -0.57
     amea
    -0.56
     amenaza
    -0.54
     threaten
    -0.49
     of
    -0.45
     вра
    -0.39
     even
    -0.38
    Threat
    -0.38
    Redacción
    -0.38
    POSITIVE LOGITS
     Савезне
    1.09
    AndEndTag
    1.00
     виправивши
    0.97
    GEBURTSDATUM
    0.97
     betweenstory
    0.95
    WireFormatLite
    0.91
     defaultstate
    0.89
    ArrowToggle
    0.88
    awtextra
    0.88
    ValueStyle
    0.86
    Activations Density 0.316%

    No Known Activations