© 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. 547
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     different
    -0.55
     celle
    -0.52
     others
    -0.50
    なもの
    -0.50
    dAtA
    -0.49
    different
    -0.45
    тельством
    -0.44
    LoadScene
    -0.44
     each
    -0.44
     DIFFERENT
    -0.43
    POSITIVE LOGITS
     utafitiHapana
    0.68
    KURZBESCHREIBUNG
    0.67
     estekak
    0.60
    󠁢
    0.58
    hoga
    0.56
    Pozdrawiam
    0.55
     חיצוניים
    0.54
    getColumnIndex
    0.54
    viewWillAppear
    0.54
    ificato
    0.53
    Activations Density 0.007%

    No Known Activations