© 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. 4930
    Prev
    Next
    INDEX
    Explanations

    gasoline

    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
    Parcelize
    -0.61
     nahilalakip
    -0.51
    rungsseite
    -0.50
    indahan
    -0.48
     ujednoznacz
    -0.48
    glers
    -0.48
    SerializedName
    -0.48
     useStyles
    -0.48
    зулта
    -0.47
    OUND
    -0.47
    POSITIVE LOGITS
    direct
    0.61
     direct
    0.55
    Direct
    0.54
     dataSnapshot
    0.54
    PreferredItem
    0.54
    lapsingToolbar
    0.53
     Direct
    0.52
     cilia
    0.52
    keo
    0.52
    cantara
    0.51
    Activations Density 0.003%

    No Known Activations