© 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. 42529
    Prev
    Next
    INDEX
    Explanations

    crane

    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
     crank
    -1.30
    cran
    -1.12
     cran
    -1.02
    crank
    -1.01
     Crank
    -1.00
     timely
    -0.96
     crane
    -0.96
    Cran
    -0.92
     cranks
    -0.90
     Crane
    -0.86
    POSITIVE LOGITS
    baar
    0.49
    eter
    0.47
    herited
    0.47
    ercises
    0.46
    ets
    0.44
    __["
    0.44
     indisponible
    0.43
    horesis
    0.43
    ewel
    0.41
    __))
    0.41
    Activations Density 1.326%

    No Known Activations