© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11327
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     stabilisation
    -0.51
    quiao
    -0.50
    ristan
    -0.49
    loem
    -0.48
     optimisation
    -0.48
    ricultural
    -0.48
    poptotic
    -0.47
    wikimedia
    -0.47
     distributed
    -0.47
    rmtree
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.74
     चीज़ों
    0.71
     resourceCulture
    0.69
     initComponents
    0.66
     defaultstate
    0.66
    tagHelperRunner
    0.64
    webElementXpaths
    0.62
    providedIn
    0.61
    tonode
    0.61
    EndInit
    0.61
    Activations Density 0.068%

    No Known Activations