© 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. 5-CLT-HP
    4. 2048
    Prev
    Next
    INDEX
    Explanations

    state

    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
     의미
    -0.59
    意味
    -0.59
     meaningfully
    -0.54
     signifie
    -0.53
     meaning
    -0.51
    の意味
    -0.51
     significa
    -0.51
     simbo
    -0.49
     means
    -0.49
     meaningful
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.67
    RenderAtEndOf
    0.64
     виправивши
    0.63
    principalTable
    0.62
     uVar
    0.60
     referenties
    0.60
    shafen
    0.59
    spots
    0.59
    ViewFeatures
    0.57
    bcryptjs
    0.56
    Activations Density 0.006%

    No Known Activations