© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92039
    Prev
    Next
    INDEX
    Explanations

    belongings

    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
     clothes
    -1.16
     ſmall
    -1.13
     foods
    -1.11
     Jefus
    -1.10
     pleaſure
    -1.10
     Theſe
    -1.09
     itſelf
    -1.05
     purpoſe
    -1.03
     reaſon
    -1.02
     houſe
    -1.02
    POSITIVE LOGITS
    exitRule
    0.49
     and
    0.49
     like
    0.48
    .
    0.48
     meant
    0.46
     in
    0.45
     to
    0.45
     for
    0.41
    ,
    0.40
     Audiodateien
    0.40
    Activations Density 0.088%

    No Known Activations