© 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. 1-CLT-HP
    4. 11848
    Prev
    Next
    INDEX
    Explanations

    long

    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
    longer
    -0.88
     longer
    -0.84
    long
    -0.82
     long
    -0.79
    longest
    -0.77
     disambiguazione
    -0.77
     يتيمه
    -0.76
    Longer
    -0.75
     LONG
    -0.75
    Enllaces
    -0.74
    POSITIVE LOGITS
     pleaf
    0.44
     whoſe
    0.42
     mence
    0.42
    ViewState
    0.42
     malam
    0.41
     hlm
    0.41
    stdbool
    0.40
     Monfieur
    0.40
     sumpay
    0.40
    ApiModel
    0.40
    Activations Density 0.154%

    No Known Activations