© 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. 92109
    Prev
    Next
    INDEX
    Explanations

    facing

    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
     facing
    -3.58
     Facing
    -2.91
    facing
    -2.89
    Facing
    -2.72
     faced
    -1.51
     confronting
    -1.34
     menghadapi
    -1.30
     enfrentar
    -1.26
     enfrentan
    -1.22
    faced
    -1.20
    POSITIVE LOGITS
     the
    0.73
     a
    0.66
     an
    0.61
     something
    0.49
     some
    0.49
     your
    0.48
     ***!
    0.47
     this
    0.47
     its
    0.47
     dry
    0.47
    Activations Density 0.144%

    No Known Activations