© 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. 95058
    Prev
    Next
    INDEX
    Explanations

    lose

    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
    mybatisplus
    -0.65
    \{\\
    -0.63
    醐
    -0.57
     TextAppearance
    -0.56
     vậy
    -0.55
    itename
    -0.55
    momix
    -0.54
    rlrl
    -0.52
    참고
    -0.52
    ficulty
    -0.50
    POSITIVE LOGITS
    MessageOf
    0.61
     Meksiku
    0.56
    Vidite
    0.56
    tvguidetime
    0.52
     [*]
    0.52
    SourceChecksum
    0.51
    autoreleasepool
    0.51
    Others
    0.50
     shalt
    0.49
    HasColumnName
    0.48
    Activations Density 0.031%

    No Known Activations