© 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. 42249
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
     a
    -0.75
     cu
    -0.48
     trekken
    -0.48
     sent
    -0.47
    sembles
    -0.47
    checs
    -0.47
     AssemblyVersion
    -0.44
    )>=
    -0.43
    ]>=
    -0.43
     adil
    -0.43
    POSITIVE LOGITS
     autorytatywna
    1.03
    ंदीखरीदारी
    0.86
    OGND
    0.79
     Roskov
    0.74
     pleaſure
    0.73
     Jefus
    0.73
     neceff
    0.71
     itſelf
    0.71
    sizeCache
    0.70
    ⓘ
    0.70
    Activations Density 0.062%

    No Known Activations