© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    Forests and tundra

    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
     hObject
    -0.52
    transQ
    -0.52
    WithIOException
    -0.50
     Fiore
    -0.45
    gpu
    -0.44
    est
    -0.42
    estä
    -0.41
    izaron
    -0.41
    ering
    -0.41
     estekak
    -0.41
    POSITIVE LOGITS
     actionMode
    0.60
    coroutines
    0.58
    IBOutlet
    0.56
    getRuntime
    0.56
    rsiniz
    0.56
    rovnik
    0.56
    +#+#
    0.53
    lgari
    0.53
     næ
    0.53
     Manif
    0.52
    Activations Density 0.351%

    No Known Activations