© 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. 20-CLT-HP
    7. 75090
    Prev
    Next
    INDEX
    Explanations

    AS

    np_max-act-logits · 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
    Diwedd
    -0.53
    __':
    -0.51
    DECREF
    -0.49
    ázky
    -0.49
    taj
    -0.47
    nteral
    -0.46
    ulipas
    -0.46
     πρέπει
    -0.46
    ใช่
    -0.45
     rowspan
    -0.45
    POSITIVE LOGITS
    TagMode
    0.60
    NameInMap
    0.58
     disambiguazione
    0.56
    olat
    0.47
    atable
    0.47
    UserScript
    0.47
    openha
    0.46
     hà
    0.46
    ровку
    0.46
    hawa
    0.45
    Activations Density 0.000%

    No Known Activations