© 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. 1-CLT-HP
    7. 10221
    Prev
    Next
    INDEX
    Explanations

    knee and growth factors

    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
     conosco
    -0.49
     regulares
    -0.47
     creciente
    -0.45
     regolare
    -0.44
    かわらず
    -0.44
     pravidel
    -0.44
     moindre
    -0.44
     Valladolid
    -0.44
     giudi
    -0.43
     nazionale
    -0.42
    POSITIVE LOGITS
    новништво
    0.68
    èdia
    0.61
    AndEndTag
    0.60
    AddTagHelper
    0.59
    abestanden
    0.59
    SOUNDBITE
    0.59
    MockMvc
    0.57
    ArgsConstructor
    0.57
    ISupport
    0.56
     Lasso
    0.54
    Activations Density 0.169%

    No Known Activations