© 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. 5-CLT-HP
    7. 75
    Prev
    Next
    INDEX
    Explanations

    Part 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
     AttributeSet
    -0.59
     of
    -0.59
     appunto
    -0.55
    Ibid
    -0.55
     complètes
    -0.53
    archiviato
    -0.52
    Question
    -0.52
     prochain
    -0.51
    AspNet
    -0.50
     sekali
    -0.50
    POSITIVE LOGITS
    stones
    0.65
     Audiodateien
    0.61
     elephants
    0.59
     resourceCulture
    0.56
     piety
    0.55
     pebbles
    0.54
    äumt
    0.54
    >{@
    0.53
    "]);
    0.53
    eapples
    0.52
    Activations Density 0.002%

    No Known Activations