© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    0

    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
    tagHelperRunner
    -0.73
    contentLoaded
    -0.71
    TagMode
    -0.69
     protoimpl
    -0.65
     hObject
    -0.64
    tagext
    -0.61
    شهاد
    -0.61
    styleType
    -0.61
     nothwendig
    -0.60
     dieß
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.51
    Tembelea
    0.47
    SL
    0.43
    MV
    0.42
     Set
    0.42
     Vainqueur
    0.42
     Mine
    0.42
    Set
    0.42
    SEM
    0.40
     KOM
    0.40
    Activations Density 0.013%

    No Known Activations