© 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. 91565
    Prev
    Next
    INDEX
    Explanations

    research and investigation

    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
    complexContent
    -0.75
    Filmografie
    -0.71
    acağına
    -0.69
     Roskov
    -0.65
    /−
    -0.63
    AddTagHelper
    -0.63
    cessite
    -0.59
    /*
    -0.58
    Conclu
    -0.57
     tramonto
    -0.57
    POSITIVE LOGITS
    MLLoader
    0.52
     يتيمه
    0.49
     follow
    0.49
    Спасылкі
    0.47
    TintMode
    0.44
    euse
    0.44
    principalColumn
    0.43
     modelling
    0.42
    UnsafeEnabled
    0.41
     mothers
    0.41
    Activations Density 0.000%

    No Known Activations