© 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. 43289
    Prev
    Next
    INDEX
    Explanations

    previous

    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
     previous
    -1.89
    previous
    -1.65
    Previous
    -1.59
     Previous
    -1.59
     previously
    -1.57
     PREVIOUS
    -1.55
     Previously
    -1.36
    Previously
    -1.34
    previously
    -1.32
     предыду
    -1.28
    POSITIVE LOGITS
    withIdentifier
    0.88
    TagMode
    0.82
     häl
    0.60
    featureID
    0.53
    #
    0.50
     "..\..\
    0.49
    ñones
    0.48
    Vidite
    0.47
    tlement
    0.47
    νι
    0.47
    Activations Density 0.149%

    No Known Activations