© 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. 10017
    Prev
    Next
    INDEX
    Explanations

    historical contexts

    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
    parral
    -0.56
    ained
    -0.49
    X
    -0.41
     form
    -0.40
     the
    -0.38
    onee
    -0.37
     his
    -0.37
    phi
    -0.36
    ct
    -0.36
     +
    -0.36
    POSITIVE LOGITS
    ]--;
    0.92
     Normdatei
    0.92
    PreferredItem
    0.89
    Begriffsklä
    0.89
    UserScript
    0.88
     uſed
    0.88
     '\\;'
    0.84
     disponibilités
    0.83
    featureID
    0.82
    AccessorTable
    0.82
    Activations Density 0.627%

    No Known Activations