© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9215
    Prev
    Next
    INDEX
    Explanations

    Real, tangible existence

    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
    TintMode
    -0.65
     realise
    -0.65
     realises
    -0.65
     محفوظة
    -0.59
     realising
    -0.57
     sebenar
    -0.57
     realised
    -0.57
     realisation
    -0.56
     nemlig
    -0.56
    writeField
    -0.54
    POSITIVE LOGITS
     world
    0.62
    world
    0.57
    setViewportView
    0.54
    Rè
    0.51
    BeginContext
    0.48
    lês
    0.48
    InlineData
    0.48
    StoryboardSegue
    0.46
    世界的
    0.45
    >{"
    0.45
    Activations Density 0.015%

    No Known Activations