© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96759
    Prev
    Next
    INDEX
    Explanations

    Mosquito

    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
    prefixer
    -0.67
    tagext
    -0.63
     TextAppearance
    -0.56
    igshid
    -0.56
    RenderAtEndOf
    -0.52
    FormState
    -0.50
     Ver
    -0.48
     chắn
    -0.47
    enten
    -0.45
     EconPapers
    -0.45
    POSITIVE LOGITS
     >=",
    0.65
     Wikimedijinoj
    0.57
    PreferredItem
    0.56
    }{*}{}
    0.53
     cherchés
    0.52
    GEBURTSDATUM
    0.52
    SBATCH
    0.52
     vectors
    0.52
    \"");
    0.52
     Lala
    0.51
    Activations Density 0.000%

    No Known Activations