© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    absorption

    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
     initComponents
    -0.60
    Lähteet
    -0.57
    Hentet
    -0.51
    Composable
    -0.49
    useEffect
    -0.48
     Geist
    -0.48
    Bronnen
    -0.47
    CrossRef
    -0.47
    tagHelperRunner
    -0.45
    [::-
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.66
    rawDesc
    0.59
    ༘
    0.59
     <>",
    0.57
    djangoproject
    0.54
     Donat
    0.54
     Италијани
    0.53
    wixt
    0.50
    Vidite
    0.50
    inalis
    0.50
    Activations Density 0.001%

    No Known Activations