© 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. 2001
    Prev
    Next
    INDEX
    Explanations

    code or data analysis

    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
    sonaro
    -0.51
    jestel
    -0.45
    romycin
    -0.44
    poso
    -0.43
    eriks
    -0.42
    asikan
    -0.42
    aric
    -0.41
    пресс
    -0.41
     zich
    -0.40
    wijl
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.93
    Autoritní
    0.80
    WithIOException
    0.78
     betweenstory
    0.78
     ProtoMessage
    0.76
    oredCriteria
    0.75
    AndEndTag
    0.75
     виправивши
    0.74
     cleanliness
    0.74
    aarrggbb
    0.73
    Activations Density 0.006%

    No Known Activations