© 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. 1-CLT-HP
    7. 9949
    Prev
    Next
    INDEX
    Explanations

    penned

    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
    
    -0.68
    SourceChecksum
    -0.64
    Season
    -0.61
    öße
    -0.61
     Season
    -0.61
    DispatchToProps
    -0.60
    KommentareTeilen
    -0.59
    BagConstraints
    -0.59
    Theme
    -0.58
    tagHelperRunner
    -0.57
    POSITIVE LOGITS
    اں
    0.56
    IComponent
    0.48
    sam
    0.47
    <%=
    0.47
    s
    0.47
    sant
    0.44
    cking
    0.42
     تضيفلها
    0.42
     You
    0.42
    Uninitialized
    0.42
    Activations Density 0.066%

    No Known Activations