© 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. 0-CLT-HP
    7. 1230
    Prev
    Next
    INDEX
    Explanations

    medical/technical reports

    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
    hirt
    -0.66
    uasion
    -0.60
    e
    -0.59
    y
    -0.58
     M
    -0.56
    ی
    -0.56
    s
    -0.55
    es
    -0.51
    er
    -0.51
    ся
    -0.50
    POSITIVE LOGITS
     Monfieur
    1.34
     Efq
    1.33
     Houſe
    1.21
     houſe
    1.18
     myſelf
    1.18
    ſelf
    1.17
     Jefus
    1.14
     themſelves
    1.13
     Majefty
    1.13
     Theſe
    1.11
    Activations Density 0.171%

    No Known Activations