© 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. 95240
    Prev
    Next
    INDEX
    Explanations

    programming questions

    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
    __':
    -0.64
    unately
    -0.63
     onely
    -0.57
    
    -0.57
    άνει
    -0.56
     faſt
    -0.56
     सकते
    -0.55
    uxta
    -0.55
    __':
    -0.55
    uests
    -0.55
    POSITIVE LOGITS
    ,
    0.90
     they
    0.64
    GEBURTSDATUM
    0.61
     I
    0.60
     AppBundle
    0.53
    they
    0.49
     CURIAM
    0.47
    ,\
    0.46
     when
    0.45
     они
    0.44
    Activations Density 0.027%

    No Known Activations