© 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. 97126
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Efq
    -1.37
    ^(@)
    -1.36
     Majefty
    -1.23
     Jefus
    -1.20
     iſt
    -1.17
    ſelf
    -1.08
     uſed
    -1.08
    ſelves
    -1.06
     doubtnut
    -1.06
     Houſe
    -1.05
    POSITIVE LOGITS
    '
    1.08
    ↵
    1.00
    ↵↵
    0.96
    <bos>
    0.89
    "
    0.84
    o
    0.83
    is
    0.82
    A
    0.82
    G
    0.82
    ’
    0.82
    Activations Density 0.232%

    No Known Activations