© 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. 1-CLT-HP
    7. 13391
    Prev
    Next
    INDEX
    Explanations

    Asking for help

    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
    versary
    -0.55
     hablado
    -0.50
     adversary
    -0.47
    isbury
    -0.47
     religiosos
    -0.42
     hayvan
    -0.42
    varu
    -0.42
    varlak
    -0.41
     colectivos
    -0.40
    Spit
    -0.40
    POSITIVE LOGITS
    XmlAccessType
    0.92
    featureID
    0.91
    MLLoader
    0.84
    tvguidetime
    0.76
    typeparam
    0.75
    basicConfig
    0.74
    ResumeLayout
    0.72
     snippetHide
    0.71
    adə
    0.71
    CloseOperation
    0.69
    Activations Density 0.214%

    No Known Activations