© 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. 0-CLT-HP
    7. 38908
    Prev
    Next
    INDEX
    Explanations

    however

    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
     entanto
    -2.11
     however
    -1.78
    however
    -1.78
     però
    -1.63
     porém
    -1.55
     tuttavia
    -1.46
     THOUGH
    -1.43
     însă
    -1.43
    However
    -1.42
     cependant
    -1.42
    POSITIVE LOGITS
    ,
    1.28
     the
    0.91
     this
    0.75
     a
    0.69
     it
    0.68
     I
    0.65
     their
    0.63
     these
    0.63
    .
    0.62
     we
    0.60
    Activations Density 0.093%

    No Known Activations