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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2173
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     AssemblyCulture
    -0.79
     مشين
    -0.60
    ScopeManager
    -0.58
    astify
    -0.57
    igre
    -0.52
    yntaxException
    -0.52
    FromNib
    -0.51
    Bloc
    -0.51
    ailleurs
    -0.50
    PMailer
    -0.50
    POSITIVE LOGITS
    abestanden
    0.81
     ujednoznacz
    0.66
    Portály
    0.59
    lahraga
    0.54
     détru
    0.52
     >=",
    0.52
     âgé
    0.51
    ########.
    0.50
    তথ্যসূত্র
    0.50
     rotina
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.