© 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. 1-CLT-HP
    7. 875
    Prev
    Next
    INDEX
    Explanations

    decision

    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
    Decisions
    -1.50
    decision
    -1.35
    Decision
    -1.31
     decision
    -1.30
     Decisions
    -1.30
    decisions
    -1.29
     DECISION
    -1.28
     Decision
    -1.27
     decisions
    -1.21
     décision
    -1.14
    POSITIVE LOGITS
     يتيمه
    0.41
     Points
    0.38
     point
    0.37
    _();
    0.36
     kit
    0.35
     Raising
    0.35
     scrap
    0.34
    ಟ
    0.34
    complexType
    0.34
    Abp
    0.34
    Activations Density 0.010%

    No Known Activations