© 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. 0-CLT-HP
    7. 40643
    Prev
    Next
    INDEX
    Explanations

    ideal

    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
     ideal
    -0.93
    ath
    -0.73
    be
    -0.66
    ideal
    -0.64
     idéal
    -0.63
     referred
    -0.59
    phy
    -0.55
    <bos>
    -0.54
     ver
    -0.53
     one
    -0.53
    POSITIVE LOGITS
     Majefty
    1.00
     myſelf
    0.94
     Houſe
    0.94
     poffible
    0.93
     Chriftian
    0.92
     itſelf
    0.92
     doubtnut
    0.90
    RenderAtEndOf
    0.88
     houſe
    0.87
     صوتيه
    0.87
    Activations Density 0.647%

    No Known Activations