© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4424
    Prev
    Next
    INDEX
    Explanations

    ac

    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
    TagMode
    -0.54
    endpush
    -0.46
    những
    -0.44
    EXTER
    -0.43
    Axe
    -0.42
    pett
    -0.42
    *}
    -0.42
    aih
    -0.41
    rceil
    -0.41
    cách
    -0.41
    POSITIVE LOGITS
     ReactDOM
    0.62
    GetKeyDown
    0.57
     متعلقه
    0.56
    tivism
    0.55
     unbroken
    0.54
     hObject
    0.53
     виправивши
    0.52
    onAttach
    0.52
    CloseOperation
    0.51
    nungs
    0.50
    Activations Density 0.000%

    No Known Activations