© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    converts

    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
    olf
    -0.63
    low
    -0.53
    cad
    -0.52
     converts
    -0.52
    outh
    -0.51
    inton
    -0.51
    lig
    -0.49
     coordinating
    -0.47
    weich
    -0.46
    sizeCache
    -0.45
    POSITIVE LOGITS
     AttributeSet
    0.73
    帖最后由
    0.63
    resaid
    0.63
    σθαι
    0.62
     assessors
    0.61
    ázaro
    0.60
    artifactId
    0.59
    NUMX
    0.59
     MotionEvent
    0.58
    MIDDLEWARE
    0.58
    Activations Density 0.082%

    No Known Activations