© 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. 5-CLT-HP
    7. 91961
    Prev
    Next
    INDEX
    Explanations

    continuation

    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
    RunWith
    -0.59
    stamo
    -0.59
    ULATOR
    -0.57
    fford
    -0.56
     Then
    -0.54
    urant
    -0.54
     Glä
    -0.54
    ungs
    -0.53
    ContentAlignment
    -0.53
     then
    -0.53
    POSITIVE LOGITS
    UnknownFields
    0.59
    IBarButtonItem
    0.49
    нциклопедия
    0.46
    liato
    0.46
     about
    0.46
     Rabin
    0.45
    Portale
    0.44
     to
    0.44
     knocking
    0.43
     Şi
    0.42
    Activations Density 0.002%

    No Known Activations