© 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. 5-CLT-HP
    4. 483
    Prev
    Next
    INDEX
    Explanations

    will

    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
     linkovi
    -0.71
    orianCalendar
    -0.70
    不需要
    -0.68
    rungsseite
    -0.67
    只需要
    -0.65
     nemus
    -0.63
    windowFixed
    -0.63
    只要
    -0.60
     behövs
    -0.60
     onPostExecute
    -0.59
    POSITIVE LOGITS
     AttributeSet
    0.48
    httphttps
    0.44
    hami
    0.43
     Kanton
    0.40
     Jurisdiction
    0.40
     词
    0.37
    سى
    0.37
     Judas
    0.37
    KEYCODE
    0.37
     Chronicle
    0.36
    Activations Density 0.003%

    No Known Activations