© 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. 514
    Prev
    Next
    INDEX
    Explanations

    remission

    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
     remission
    -1.56
     pinulongan
    -0.72
    ripsi
    -0.71
    rzost
    -0.67
    extAlignment
    -0.66
     spéciale
    -0.65
     ComVisible
    -0.65
     représ
    -0.63
     pourriez
    -0.62
    WithMany
    -0.61
    POSITIVE LOGITS
    ness
    0.77
    IComponent
    0.62
    st
    0.53
    t
    0.53
    ers
    0.52
    ThroughAttribute
    0.52
    Tikang
    0.50
    kloped
    0.48
    EndGlobalSection
    0.48
    stus
    0.44
    Activations Density 0.010%

    No Known Activations