© 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. 1-CLT-HP
    7. 45851
    Prev
    Next
    INDEX
    Explanations

    brake substrate

    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
     chi̍t
    -0.51
     الاطلاع
    -0.46
    Identyfik
    -0.45
    примеча
    -0.45
    sels
    -0.45
    ry
    -0.44
    OGND
    -0.43
    standers
    -0.42
    tha
    -0.42
    tosa
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    EndContext
    0.68
     localObject
    0.64
    tagext
    0.59
    Xaml
    0.56
     pageSize
    0.56
    <?
    0.55
     Pager
    0.53
     indestru
    0.53
     useEffect
    0.53
    Activations Density 0.043%

    No Known Activations