© 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. 96845
    Prev
    Next
    INDEX
    Explanations

    medicine and restoration

    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
    <bos>
    -0.49
     regretted
    -0.45
     life
    -0.44
    into
    -0.38
     of
    -0.38
     vital
    -0.37
    न्द
    -0.37
     into
    -0.36
    dari
    -0.36
    attori
    -0.36
    POSITIVE LOGITS
    InjectAttribute
    0.90
    Personendaten
    0.90
    tagHelperRunner
    0.88
    jstor
    0.79
    +#+#
    0.73
     referrerpolicy
    0.72
     CanadaChoose
    0.71
    PhysRevD
    0.70
     Picchu
    0.68
    hyrchwyd
    0.67
    Activations Density 0.003%

    No Known Activations