© 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. 96494
    Prev
    Next
    INDEX
    Explanations

    likelihood

    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
     Disposition
    -0.51
    VA
    -0.48
    ChildScrollView
    -0.47
    len
    -0.45
    ̀nh
    -0.44
    endl
    -0.44
    ORI
    -0.43
    inama
    -0.42
     getItemId
    -0.42
    va
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.85
     ratio
    0.71
     pinulongan
    0.68
    s
    0.68
    WriteTagHelper
    0.68
     ratios
    0.65
    ratios
    0.65
    RATIO
    0.65
    MigrationBuilder
    0.64
    ratio
    0.63
    Activations Density 0.001%

    No Known Activations