© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 664
    Prev
    Next
    INDEX
    Explanations

    code

    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
    rungsseite
    -0.75
    protoimpl
    -0.71
     חיצוניים
    -0.71
     مشين
    -0.71
    Abit
    -0.69
    ContentAsync
    -0.67
    RegistryLite
    -0.66
    Personendaten
    -0.66
     صوتيه
    -0.65
     udaler
    -0.63
    POSITIVE LOGITS
    mesin
    0.44
     IOError
    0.43
    feinander
    0.43
    issaient
    0.41
     CCM
    0.41
    CDCl
    0.39
    meanor
    0.37
    flé
    0.36
    setDo
    0.36
    markt
    0.35
    Activations Density 0.001%

    No Known Activations