© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11457
    Prev
    Next
    INDEX
    Explanations

    "see also" or references

    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
    uities
    -2.50
    uity
    -1.16
     useAppContext
    -0.81
    MigrationBuilder
    -0.78
     للمعارف
    -0.77
     CreateTagHelper
    -0.77
    NUMX
    -0.76
     defaultstate
    -0.75
    GraphicsUnit
    -0.73
     ujednoznacz
    -0.73
    POSITIVE LOGITS
    d
    0.50
    dy
    0.45
    ely
    0.44
     blok
    0.44
     egens
    0.44
     boucles
    0.44
    dm
    0.43
    tor
    0.42
     limón
    0.42
    leaner
    0.42
    Activations Density 0.024%

    No Known Activations