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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39552
    Prev
    Next
    INDEX
    Explanations

    bleeding

    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
     glass
    -0.94
     bleeding
    -0.81
     Glass
    -0.67
    Glass
    -0.61
    glass
    -0.59
     GLASS
    -0.59
    玻璃
    -0.57
     Old
    -0.55
    ガラス
    -0.54
     vidrio
    -0.52
    POSITIVE LOGITS
     Мексичка
    1.30
    RenderAtEndOf
    1.20
    Hentet
    1.09
    OGND
    1.06
     betweenstory
    1.04
    posedge
    0.95
    oredCriteria
    0.94
     Signalez
    0.91
    memoized
    0.91
     JpaRepository
    0.91
    Activations Density 0.184%

    No Known Activations