© 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. 72883
    Prev
    Next
    INDEX
    Explanations

    across

    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
     AssemblyVersion
    -0.71
    Geplaatst
    -0.65
    IsContent
    -0.63
    ).]
    -0.61
    ainville
    -0.60
     Tweede
    -0.58
    tubers
    -0.57
     popsic
    -0.57
    όμε
    -0.57
    tagext
    -0.56
    POSITIVE LOGITS
     B
    0.73
     b
    0.63
    B
    0.58
     back
    0.56
     виправивши
    0.55
    ScopeManager
    0.55
     ver
    0.51
     functions
    0.51
    Functions
    0.50
    FormTagHelper
    0.50
    Activations Density 0.000%

    No Known Activations