© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10757
    Prev
    Next
    INDEX
    Explanations

    take

    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
    ons
    -0.49
    ro
    -0.46
    turn
    -0.46
    ance
    -0.45
    our
    -0.45
    Turn
    -0.44
    ρο
    -0.44
    ka
    -0.43
    лга
    -0.43
     Turn
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.81
    featureID
    0.74
    OCCURRED
    0.71
    }\]
    0.70
    Diweddarwch
    0.68
    medades
    0.68
     pinulongan
    0.68
     withal
    0.68
    SharedDtor
    0.67
     tartalomajánló
    0.66
    Activations Density 0.002%

    No Known Activations