© 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. 0-CLT-HP
    7. 42870
    Prev
    Next
    INDEX
    Explanations

    concentrations

    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
     solids
    -0.61
     ddelweddau
    -0.60
    áld
    -0.60
    behaviour
    -0.59
    gonic
    -0.57
    MarshalTo
    -0.54
    mappedBy
    -0.53
    flav
    -0.51
    νή
    -0.51
    ThemeOverlay
    -0.51
    POSITIVE LOGITS
    landır
    0.59
    colhead
    0.59
    EndTag
    0.58
    s
    0.57
     kaynağından
    0.56
     onItemClick
    0.54
     CreateTagHelper
    0.53
    shim
    0.50
    sn
    0.49
    mustang
    0.48
    Activations Density 1.313%

    No Known Activations