© 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. 5-CLT-HP
    7. 2021
    Prev
    Next
    INDEX
    Explanations

    code, formulas

    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
    Mi
    -0.76
    oneofs
    -0.73
    tagHelperRunner
    -0.72
    Ra
    -0.69
    Cle
    -0.67
    Sa
    -0.67
    Jr
    -0.66
    A
    -0.66
    Ker
    -0.66
    Ri
    -0.66
    POSITIVE LOGITS
    Παραπομπές
    0.63
     L
    0.45
     B
    0.44
     J
    0.42
     C
    0.42
     S
    0.41
     V
    0.39
     R
    0.38
     M
    0.37
     G
    0.37
    Activations Density 0.006%

    No Known Activations