© 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. 40665
    Prev
    Next
    INDEX
    Explanations

    lasts

    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
    lasts
    -0.75
     purpoſe
    -0.75
     pleaſure
    -0.68
     reaſon
    -0.67
     houſe
    -0.67
     <=",
    -0.66
     myſelf
    -0.64
     expulsion
    -0.63
     ſtate
    -0.62
     podjela
    -0.61
    POSITIVE LOGITS
    MLLoader
    0.69
    setopt
    0.57
    setLayoutManager
    0.53
    __(/*!
    0.53
     juridiques
    0.53
    EDEFAULT
    0.51
    StandardCharsets
    0.48
     biografias
    0.48
    BlockingQueue
    0.48
    oporosis
    0.48
    Activations Density 0.039%

    No Known Activations