© 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. 20-CLT-HP
    7. 72625
    Prev
    Next
    INDEX
    Explanations

    ad

    np_max-act-logits · 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
     @"/
    -0.58
    ISupport
    -0.49
    ślę
    -0.48
    OGND
    -0.47
     TestBed
    -0.47
    قایناقلار
    -0.47
    reactivex
    -0.46
    pyx
    -0.46
    Big
    -0.43
    lagem
    -0.42
    POSITIVE LOGITS
    ulter
    0.73
    versaries
    0.69
    wares
    0.55
    zuli
    0.55
     GenerationType
    0.54
    BackStack
    0.54
    __(/*!
    0.53
    ulator
    0.53
    versary
    0.53
    uler
    0.52
    Activations Density 0.001%

    No Known Activations