© 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. 269
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
     виправивши
    -0.81
     createSlice
    -0.72
    Diweddarwch
    -0.66
     betweenstory
    -0.66
     препратки
    -0.65
     nakalista
    -0.65
     <<<<<<<<<<<<<<
    -0.63
     endwhile
    -0.62
    neman
    -0.61
    aarrggbb
    -0.60
    POSITIVE LOGITS
    foot
    0.50
    ft
    0.50
    blurRadius
    0.50
    pond
    0.49
     to
    0.49
    mi
    0.48
    pot
    0.48
    -
    0.47
    rain
    0.47
    gro
    0.47
    Activations Density 0.010%

    No Known Activations