© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1423
    Prev
    Next
    INDEX
    Explanations

    Soviet

    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
    StoryboardSegue
    -0.79
     Chwiliwch
    -0.74
    Hochspringen
    -0.73
     fallu
    -0.73
     للمعارف
    -0.73
    EndGlobalSection
    -0.71
     ExecuteAsync
    -0.68
     autorytatywna
    -0.67
     OMITBAD
    -0.67
    RunWith
    -0.65
    POSITIVE LOGITS
     Union
    0.69
    -
    0.51
     past
    0.47
    s
    0.46
     Jewish
    0.45
    niana
    0.43
    #/
    0.42
     black
    0.42
     $__
    0.42
     fixation
    0.42
    Activations Density 0.001%

    No Known Activations