© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39006
    Prev
    Next
    INDEX
    Explanations

    Ger

    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
     
    -0.72
     ger
    -0.67
     a
    -0.67
     gel
    -0.63
     c
    -0.62
    ,
    -0.61
     (
    -0.57
     y
    -0.57
     le
    -0.57
     de
    -0.56
    POSITIVE LOGITS
     itſelf
    1.30
     myſelf
    1.22
     iſt
    1.07
     Majefty
    1.05
    ſelves
    1.05
     ་་
    1.05
     ſind
    1.04
     ―――――
    1.04
    ſelf
    1.01
     doubtnut
    1.01
    Activations Density 0.371%

    No Known Activations