© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43659
    Prev
    Next
    INDEX
    Explanations

    erasMethod: 1Reason: MAX_ACTIVATING_TOKENS contains mostly variations of "eras", so that is the best guess.eras

    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
    eras
    -2.41
    ERAS
    -1.20
    Eras
    -0.78
    Hentet
    -0.76
     eras
    -0.75
     onCancelled
    -0.73
    erat
    -0.69
    ქ
    -0.67
    fjspx
    -0.65
    xically
    -0.63
    POSITIVE LOGITS
    Билгалдахарш
    0.54
    nemia
    0.50
    UMBUS
    0.49
    évaluateur
    0.47
     dû
    0.43
    UTERS
    0.43
    IntentFilter
    0.42
    aczy
    0.41
    RenderAtEndOf
    0.41
    Pinus
    0.41
    Activations Density 1.648%

    No Known Activations