© 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. 0-CLT-HP
    7. 1130
    Prev
    Next
    INDEX
    Explanations

    Siberia

    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
     Siberia
    -1.23
    avari
    -0.65
     flip
    -0.61
    GATE
    -0.59
     saturation
    -0.57
     pinulongan
    -0.57
    curios
    -0.57
     Overflow
    -0.56
    ThemeOverlay
    -0.56
    WriteBarrier
    -0.55
    POSITIVE LOGITS
    Portail
    0.67
    ніципалі
    0.57
    __":
    0.55
    __":
    0.53
     raggiunto
    0.53
    ibley
    0.50
     épouse
    0.50
     religieuses
    0.48
    hyrchwyd
    0.47
     progettazione
    0.47
    Activations Density 0.225%

    No Known Activations