© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
     kasarigan
    -0.82
    Autoritní
    -0.72
     Chord
    -0.58
    webElementXpaths
    -0.55
     InputDecoration
    -0.53
    EndContext
    -0.52
    cookieParser
    -0.52
     systolic
    -0.52
    archiviato
    -0.51
    amation
    -0.51
    POSITIVE LOGITS
     rendus
    0.54
     ainfi
    0.53
     chrétiens
    0.52
    FTFY
    0.52
     mauva
    0.51
     scoperta
    0.51
     détru
    0.50
     marins
    0.50
     Découvrez
    0.50
    -------
    0.49
    Activations Density 0.006%

    No Known Activations