© 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. 91309
    Prev
    Next
    INDEX
    Explanations

    mental

    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
    AsUp
    -0.84
     nahilalakip
    -0.71
    Chham
    -0.68
    ніципа
    -0.67
     محفوظة
    -0.66
     AssemblyProduct
    -0.65
    /−
    -0.63
    ItemLayout
    -0.63
    tvguidetime
    -0.62
    TypedDataSet
    -0.61
    POSITIVE LOGITS
    MLLoader
    0.44
    onimo
    0.44
    omez
    0.44
    通販
    0.42
    Télé
    0.42
    enumi
    0.42
    UnsafeEnabled
    0.42
     uintptr
    0.40
    pta
    0.40
     privé
    0.39
    Activations Density 0.002%

    No Known Activations