© 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. 0-CLT-HP
    7. 93841
    Prev
    Next
    INDEX
    Explanations

    personal narratives

    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
    ably
    -0.63
    ingly
    -0.61
    ily
    -0.54
    Rüyada
    -0.53
    kém
    -0.52
     Qualquer
    -0.52
     anything
    -0.52
    something
    -0.51
    ształ
    -0.50
    Weiterlesen
    -0.50
    POSITIVE LOGITS
    ’
    0.85
     can
    0.81
    DockStyle
    0.70
     will
    0.69
    '
    0.67
    ftagPool
    0.65
     cannot
    0.65
    LookAnd
    0.63
    UrlResolution
    0.62
     are
    0.57
    Activations Density 0.240%

    No Known Activations