© 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. 94520
    Prev
    Next
    INDEX
    Explanations

    high school

    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
    पया
    -0.57
    uvwxyz
    -0.55
    oyi
    -0.54
     halves
    -0.54
     trunks
    -0.53
     easements
    -0.53
    Group
    -0.52
     jacks
    -0.52
    Vida
    -0.51
    cmc
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.66
     School
    0.63
    principalColumn
    0.62
    school
    0.59
    LLocation
    0.57
    GraphicsUnit
    0.56
     school
    0.56
    варь
    0.54
     Normdatei
    0.53
    onAttach
    0.51
    Activations Density 0.001%

    No Known Activations