© 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. 77178
    Prev
    Next
    INDEX
    Explanations

    E. coli

    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
     defaultstate
    -0.92
     متعلقه
    -0.86
    AccessorTable
    -0.82
    AndEndTag
    -0.78
    DockStyle
    -0.78
     EconPapers
    -0.75
    WriteBarrier
    -0.75
    bootstrapcdn
    -0.75
    @[+][
    -0.73
    complexContent
    -0.73
    POSITIVE LOGITS
    hi
    0.45
    Coil
    0.44
    シング
    0.43
    View
    0.38
    char
    0.37
     useAuth
    0.37
    フリ
    0.37
     fa
    0.36
     charakter
    0.36
     Fa
    0.35
    Activations Density 0.006%

    No Known Activations