© 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. 0-CLT-HP
    7. 95071
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
     saving
    -0.81
     Forward
    -0.73
    ValueStyle
    -0.66
    ness
    -0.63
    Forward
    -0.60
    ari
    -0.56
    ########.
    -0.55
    setof
    -0.53
    saving
    -0.50
    WriteTagHelper
    -0.50
    POSITIVE LOGITS
     سكانية
    0.58
     gepubliceerd
    0.55
    DeleteBehavior
    0.55
    HasKey
    0.50
    پیوند
    0.49
     Administrativna
    0.48
     bianche
    0.48
    parsedMessage
    0.48
    Ideal
    0.47
    DockStyle
    0.47
    Activations Density 0.942%

    No Known Activations