© 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. 92149
    Prev
    Next
    INDEX
    Explanations

    devotion

    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
     moonlight
    -0.77
     Shakspeare
    -0.77
     constitution
    -0.77
    evening
    -0.76
     Jérusalem
    -0.73
     season
    -0.72
     evening
    -0.68
    AutoresizingMask
    -0.68
    genus
    -0.68
     étoient
    -0.67
    POSITIVE LOGITS
    ality
    0.90
    als
    0.83
    ally
    0.80
    ly
    0.79
    ness
    0.76
    ary
    0.74
    ial
    0.73
    ry
    0.72
    less
    0.71
    ment
    0.70
    Activations Density 0.066%

    No Known Activations