© 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. 0-CLT-HP
    7. 93804
    Prev
    Next
    INDEX
    Explanations

    usually/generally

    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
    wad
    -0.65
    Usually
    -0.58
    evos
    -0.54
     Usually
    -0.54
     fascinated
    -0.48
    dsn
    -0.48
     creía
    -0.47
    HasBeenSet
    -0.45
    算了
    -0.45
    ی
    -0.44
    POSITIVE LOGITS
     JpaRepository
    0.67
     TextAppearance
    0.66
    NUMX
    0.64
    iffion
    0.63
     lifetimes
    0.61
    ControllerTest
    0.61
    RunWith
    0.60
    LLocation
    0.60
     XNUMX
    0.60
     BoxFit
    0.60
    Activations Density 0.177%

    No Known Activations