© 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. 971
    Prev
    Next
    INDEX
    Explanations

    implying

    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
     aware
    -0.98
    aware
    -0.88
     незавершена
    -0.77
    findpost
    -0.70
     indicating
    -0.65
     suggesting
    -0.65
     implying
    -0.64
    LLocation
    -0.63
     éché
    -0.60
     EClass
    -0.60
    POSITIVE LOGITS
     Theſe
    0.65
     OMIT
    0.59
     Efq
    0.58
    ')));
    0.57
    ngs
    0.57
     itſelf
    0.57
     }));
    0.56
    ymas
    0.56
    '},
    
    0.56
     himſelf
    0.55
    Activations Density 0.038%

    No Known Activations