© 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. 4-CLT-HP
    7. 91
    Prev
    Next
    INDEX
    Explanations

    intercepting/capturing data

    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
     CreateTagHelper
    -0.54
    StoryboardSegue
    -0.53
    :✨
    -0.53
     jouet
    -0.51
    BeginInit
    -0.50
    ExtendWith
    -0.49
    KURZBESCHREIBUNG
    -0.48
    PageRoute
    -0.47
    sept
    -0.47
    æring
    -0.46
    POSITIVE LOGITS
     conversations
    0.61
    ietf
    0.59
     <<<<<<<<<<<<<<
    0.57
     and
    0.55
    omiast
    0.53
    conversations
    0.52
    Népesség
    0.51
    INCREF
    0.51
     discussions
    0.50
    lük
    0.50
    Activations Density 0.020%

    No Known Activations