© 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. 2084
    Prev
    Next
    INDEX
    Explanations

    to

    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
     do
    -0.56
     appear
    -0.51
     remind
    -0.49
    ształ
    -0.47
     look
    -0.47
     hint
    -0.45
     cite
    -0.45
     see
    -0.44
     simulate
    -0.44
     المعيارى
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
     the
    0.65
     when
    0.63
    ,:);
    0.63
     الحره
    0.62
    SPATH
    0.59
    capace
    0.59
     '+':
    0.57
     mourut
    0.57
     Majefty
    0.57
    Activations Density 0.001%

    No Known Activations