© 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. 5-CLT-HP
    4. 94354
    Prev
    Next
    INDEX
    Explanations

    of

    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
    <eos>
    -0.63
    -
    -0.49
     that
    -0.46
    ↵↵
    -0.44
    :
    -0.39
    ...
    -0.38
     of
    -0.35
    ↵
    -0.35
    1
    -0.35
    3
    -0.33
    POSITIVE LOGITS
     Efq
    1.05
    ^(@)
    1.02
     Jefus
    0.98
     pleaſure
    0.97
    AndEndTag
    0.94
    ModelAdmin
    0.94
    IntoConstraints
    0.93
     doubtnut
    0.92
     Anſ
    0.92
     iſt
    0.91
    Activations Density 0.002%

    No Known Activations