© 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. 1855
    Prev
    Next
    INDEX
    Explanations

    allis

    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
    ensible
    -2.08
    allis
    -0.77
    fromnode
    -0.65
     Numerade
    -0.64
    ensibility
    -0.62
    AddTagHelper
    -0.61
    }));
    -0.58
     Biôgrafia
    -0.58
    opardy
    -0.57
     ComVisible
    -0.56
    POSITIVE LOGITS
    SuppressLint
    0.71
    awtextra
    0.59
     BitmapFactory
    0.59
    icznych
    0.54
    Portail
    0.51
    AndEndTag
    0.51
    MigrationBuilder
    0.51
    SystemColors
    0.50
    ink
    0.49
     rag
    0.47
    Activations Density 0.031%

    No Known Activations