© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91045
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    ▁is

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     is
    -1.50
     είναι
    -0.73
    which
    -0.68
     préc
    -0.67
     betreft
    -0.66
     является
    -0.64
    seamnă
    -0.64
    ozat
    -0.61
     représente
    -0.61
     steht
    -0.60
    POSITIVE LOGITS
     able
    0.94
     not
    0.90
     a
    0.85
     considered
    0.80
     seen
    0.79
     an
    0.75
     also
    0.74
     unable
    0.73
     based
    0.71
     capable
    0.69
    Activations Density 0.824%

    No Known Activations