© 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. 45466
    Prev
    Next
    INDEX
    Explanations

    explanations/theories

    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
     Anſ
    -1.16
     houſe
    -1.14
     Houſe
    -1.13
     purpoſe
    -1.13
     myſelf
    -1.12
     pleaſure
    -1.10
     ſmall
    -1.09
     ſche
    -1.05
     ſever
    -1.05
     Majefty
    -1.03
    POSITIVE LOGITS
     of
    0.84
     is
    0.75
    .
    0.72
     on
    0.72
     in
    0.69
    ,
    0.69
    s
    0.68
     for
    0.68
     and
    0.63
     also
    0.61
    Activations Density 0.456%

    No Known Activations