© 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. 1126
    Prev
    Next
    INDEX
    Explanations

    op/ins

    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
    ins
    -0.88
    INS
    -0.79
     INS
    -0.76
     ins
    -0.65
    op
    -0.63
    postIndex
    -0.61
    Ins
    -0.60
    🔽
    -0.59
    obis
    -0.59
     Ins
    -0.56
    POSITIVE LOGITS
    httphttps
    0.64
     jsPsych
    0.56
    yntaxException
    0.55
    orsese
    0.54
    adays
    0.51
    はじめに
    0.51
    دانشنامهٔ
    0.51
    blest
    0.49
    ništvo
    0.49
    Билгалдахарш
    0.49
    Activations Density 0.025%

    No Known Activations