© 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. 1-CLT-HP
    7. 45794
    Prev
    Next
    INDEX
    Explanations

    approval

    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
     approve
    -1.12
     approval
    -1.09
     approved
    -1.00
    approval
    -1.00
    approved
    -0.95
     APPROVAL
    -0.94
     approving
    -0.92
     Approval
    -0.91
    Approved
    -0.89
    Approval
    -0.88
    POSITIVE LOGITS
    клопе
    0.55
    Kund
    0.51
     processes
    0.44
     vitale
    0.42
     language
    0.42
    ượt
    0.42
    ágok
    0.41
    이터
    0.40
     laws
    0.40
    Craft
    0.40
    Activations Density 0.014%

    No Known Activations