© 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. 5-CLT-HP
    7. 3397
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     nakalista
    -0.70
    <bos>
    -0.55
    -------
    -0.50
    didSet
    -0.48
    inhard
    -0.48
     unanswered
    -0.46
     Gerald
    -0.46
     Alan
    -0.45
    hikari
    -0.45
    olong
    -0.44
    POSITIVE LOGITS
    دانشنامهٔ
    0.76
     autorytatywna
    0.74
     Barbier
    0.56
     wireType
    0.56
     AssemblyTitle
    0.55
     Chwiliwch
    0.55
    ]),
    0.54
    +#+#
    0.53
     виправивши
    0.53
    aarrggbb
    0.52
    Activations Density 0.003%

    No Known Activations