© 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. 5-CLT-HP
    7. 91267
    Prev
    Next
    INDEX
    Explanations

    id

    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
     linkovi
    -0.87
     Савезне
    -0.76
     présidenti
    -0.68
    хьтан
    -0.68
    ThroughAttribute
    -0.67
    RenderAtEndOf
    -0.66
     disambiguazione
    -0.66
     Majefty
    -0.66
    PreferredItem
    -0.65
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
    GL
    0.56
     GL
    0.43
    gl
    0.42
    許
    0.41
    omo
    0.41
     gl
    0.39
    MLLoader
    0.38
     my
    0.38
    my
    0.37
    Gl
    0.37
    Activations Density 0.007%

    No Known Activations