© 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. 20-CLT-HP
    7. 74709
    Prev
    Next
    INDEX
    Explanations

    audio

    np_max-act-logits · 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
    migrationBuilder
    -0.49
     intptr
    -0.48
     betweenstory
    -0.47
    клопе
    -0.45
     Momb
    -0.44
    جغرافيا
    -0.43
    Enllaces
    -0.42
    batore
    -0.42
    ρη
    -0.40
     Gaz
    -0.40
    POSITIVE LOGITS
    ########.
    0.66
     coding
    0.65
     decoding
    0.63
    AnchorStyles
    0.62
     COD
    0.61
     sink
    0.60
     onAnimation
    0.59
    ControllerAdvice
    0.58
     coder
    0.57
     decode
    0.56
    Activations Density 0.002%

    No Known Activations