© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40299
    Prev
    Next
    INDEX
    Explanations

    homo

    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
    RenderAtEndOf
    -1.07
    Vidite
    -1.02
    ernalia
    -1.01
    脚注の使い方
    -0.97
    Insee
    -0.94
    theless
    -0.93
    LEncoder
    -0.92
    MessageTagHelper
    -0.89
     مرئيه
    -0.88
    nologue
    -0.87
    POSITIVE LOGITS
     from
    0.56
     and
    0.49
    .
    0.49
    -
    0.49
     es
    0.48
     head
    0.48
    ,
    0.48
    e
    0.46
     val
    0.46
     or
    0.46
    Activations Density 0.055%

    No Known Activations