© 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. 1456
    Prev
    Next
    INDEX
    Explanations

    suggestions/recommendations

    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
    ROIT
    -0.69
    SPATH
    -0.63
     Cæsar
    -0.59
    illet
    -0.59
     LUMP
    -0.59
     scal
    -0.58
     rover
    -0.57
    vium
    -0.57
    óleo
    -0.56
    uxxxx
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.73
    клопе
    0.64
    EndGlobalSection
    0.61
    IsMutable
    0.60
     a
    0.58
     kasarigan
    0.55
    pod
    0.54
    adaptiveStyles
    0.53
    OCCURRED
    0.53
     the
    0.52
    Activations Density 0.019%

    No Known Activations