© 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. 4-CLT-HP
    7. 4305
    Prev
    Next
    INDEX
    Explanations

    .

    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
    IsMutable
    -0.54
    Phenyl
    -0.52
     StringTokenizer
    -0.52
    iprot
    -0.52
    itability
    -0.51
    ftan
    -0.50
    hicles
    -0.49
     manquante
    -0.49
     vo
    -0.48
    penup
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.81
     LUMP
    0.65
     चीज़ों
    0.57
     []:
    0.56
    存于互联网档案馆
    0.55
    jší
    0.55
    : 
    0.54
     linkovi
    0.50
    SequentialGroup
    0.49
    ultat
    0.49
    Activations Density 0.000%

    No Known Activations