© 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. 1-CLT-HP
    7. 45601
    Prev
    Next
    INDEX
    Explanations

    including or transmitting

    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
    sizeCache
    -0.84
    bearers
    -0.77
    ThroughAttribute
    -0.76
    bearer
    -0.75
     createSlice
    -0.70
    <bos>
    -0.70
     bearer
    -0.69
    Fatalf
    -0.68
    ritsar
    -0.67
    Portail
    -0.66
    POSITIVE LOGITS
     fact
    0.45
    uronic
    0.45
    maq
    0.39
     getElement
    0.38
    POSURE
    0.38
    keer
    0.38
     maxime
    0.37
    helin
    0.35
    sources
    0.35
    Kev
    0.35
    Activations Density 0.189%

    No Known Activations