© 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. 91264
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ImageContext
    -0.56
    RTGC
    -0.54
     BrowserModule
    -0.53
    icoot
    -0.53
    rano
    -0.53
     Pristupljeno
    -0.51
    INCT
    -0.51
    eynman
    -0.50
    Izvori
    -0.50
    WriteTagHelper
    -0.49
    POSITIVE LOGITS
    Hochspringen
    0.50
     שוליים
    0.49
     then
    0.48
    Then
    0.48
    آباد
    0.47
    RetentionPolicy
    0.46
    WarningLevel
    0.46
    Plusieurs
    0.45
     one
    0.45
     MOQ
    0.45
    Activations Density 0.002%

    No Known Activations