© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 788
    Prev
    Next
    INDEX
    Explanations

    audience

    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
    ScopeManager
    -0.66
    nodoc
    -0.65
    __))
    -0.65
    rungsseite
    -0.58
    jgl
    -0.58
    VersionUID
    -0.57
    providedIn
    -0.57
     StatefulWidget
    -0.56
     rayon
    -0.54
    >";
    -0.53
    POSITIVE LOGITS
     nakalista
    0.59
    autique
    0.51
    DockStyle
    0.50
    IUrlHelper
    0.49
     Testamento
    0.48
     "..\..\..\
    0.47
     dare
    0.46
    xsi
    0.46
     dares
    0.45
    brates
    0.45
    Activations Density 0.001%

    No Known Activations