© 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. 0-CLT-HP
    7. 40622
    Prev
    Next
    INDEX
    Explanations

    stasis

    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
     Pollard
    -1.03
    equal
    -0.59
    stasis
    -0.57
    $_['
    -0.57
     médicas
    -0.47
    Хьажоргаш
    -0.47
     podéis
    -0.47
     actuels
    -0.46
     faltan
    -0.46
     normaux
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.82
    IVEREF
    0.69
    CPtr
    0.63
     autorytatywna
    0.60
    ChildScrollView
    0.60
    Manbalar
    0.57
    +#+#
    0.57
    KURZBESCHREIBUNG
    0.57
    Enllaces
    0.57
     ujednoznacz
    0.57
    Activations Density 0.237%

    No Known Activations