© 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. 94990
    Prev
    Next
    INDEX
    Explanations

    and

    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
    usercontent
    -0.60
    ритори
    -0.57
    原始内容存档于
    -0.56
    <()>
    -0.56
     isInitialized
    -0.53
    ...");
    -0.52
    )​
    -0.51
     саны
    -0.51
    },[])
    -0.50
    [])
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.93
    EDEFAULT
    0.69
     disambiguazione
    0.64
    :✨
    0.62
    Personensuche
    0.61
    bewerken
    0.61
     gynhyrchwyd
    0.61
    expandindo
    0.60
     Biôgrafia
    0.59
     beginnetje
    0.57
    Activations Density 0.037%

    No Known Activations