Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91302
    Prev
    Next
    INDEX
    Explanations

    ra

    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
    ra
    -1.97
     ra
    -1.49
     Ra
    -1.30
    Ra
    -1.17
    RA
    -1.07
    rae
    -0.81
    t
    -0.81
     RA
    -0.79
    n
    -0.77
    raa
    -0.77
    POSITIVE LOGITS
     GenerationType
    0.66
     itſelf
    0.59
     myſelf
    0.59
     mergeFrom
    0.58
     uVar
    0.57
     themſelves
    0.56
     ſmall
    0.56
     crdi
    0.55
     vectorielle
    0.54
     umana
    0.54
    Activations Density 0.646%

    No Known Activations