© 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. 4-CLT-HP
    7. 2578
    Prev
    Next
    INDEX
    Explanations

    to

    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
    iksi
    -0.53
    ukses
    -0.50
    prus
    -0.50
     purpoſe
    -0.48
     veau
    -0.47
    iální
    -0.47
     hinweg
    -0.47
    ManyToMany
    -0.47
     habet
    -0.46
     itſelf
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.83
     saites
    0.72
     defaultstate
    0.71
    MLLoader
    0.65
     متعلقه
    0.64
    PyExc
    0.64
    PMailer
    0.64
    TargetException
    0.63
     pinulongan
    0.63
    antd
    0.63
    Activations Density 0.008%

    No Known Activations