© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74997
    Prev
    Next
    INDEX
    Explanations

    per

    np_max-act-logits · 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
    endios
    -0.49
    δέ
    -0.49
     GIPHY
    -0.47
    ]--;
    -0.46
    resa
    -0.46
    batore
    -0.45
     sider
    -0.45
    @@@@@
    -0.45
     spot
    -0.44
    rimi
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.84
    Gön
    0.63
    Kanpo
    0.61
    MarshalTo
    0.60
    addCriterion
    0.59
    曖昧さ回避
    0.57
    msgTypes
    0.56
    NameInMap
    0.56
    uxxxx
    0.54
    يميديا
    0.54
    Activations Density 0.003%

    No Known Activations