© 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. 5-CLT-HP
    7. 94850
    Prev
    Next
    INDEX
    Explanations

    gain

    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
     tartalomajánló
    -0.66
    HomeAsUpEnabled
    -0.50
    ecuted
    -0.49
    verwijspagina
    -0.48
    webElementXpaths
    -0.47
    matsu
    -0.47
    WriteLiteral
    -0.47
     vedea
    -0.46
     avenir
    -0.46
    Jereo
    -0.44
    POSITIVE LOGITS
     control
    0.57
    ⓧ
    0.56
    Personendaten
    0.54
     traction
    0.53
    CrossRef
    0.53
     trust
    0.53
     autorytatywna
    0.52
     admirers
    0.52
    traction
    0.52
     credibility
    0.50
    Activations Density 0.002%

    No Known Activations