© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    until

    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
     disambiguazione
    -0.63
     iaitu
    -0.58
     CommonModule
    -0.58
     بيها
    -0.57
    はじめに
    -0.57
    ikä
    -0.56
     cheminée
    -0.55
    ControllerTest
    -0.55
    #+#
    -0.55
     näm
    -0.54
    POSITIVE LOGITS
     past
    0.69
    past
    0.59
     the
    0.54
    Past
    0.51
    PAST
    0.49
     rapid
    0.48
    ünstler
    0.46
     PAST
    0.46
    wyczaj
    0.45
     early
    0.44
    Activations Density 0.002%

    No Known Activations