© 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. 5-CLT-HP
    7. 96870
    Prev
    Next
    INDEX
    Explanations

    measurements and parameters

    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
     يتيمه
    -0.60
     []:
    -0.51
     Normdatei
    -0.50
    DeleteBehavior
    -0.49
    tagHelperRunner
    -0.47
    Lähteet
    -0.46
    ----</
    -0.46
    currentColor
    -0.46
    RunWith
    -0.44
    原始内容存档
    -0.44
    POSITIVE LOGITS
     uſed
    0.62
     used
    0.61
     tracked
    0.59
    чественной
    0.59
    vertisers
    0.59
     lèvres
    0.57
    erweise
    0.57
     measure
    0.57
     vérit
    0.56
     folosit
    0.56
    Activations Density 0.000%

    No Known Activations