© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 238
    Prev
    Next
    INDEX
    Explanations

    quarter

    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
     estekak
    -0.66
     препратки
    -0.60
    ंदीखरीदारी
    -0.57
    ohjel
    -0.56
    ="#"><
    -0.55
    >--}}
    -0.55
     STUD
    -0.55
    Биография
    -0.54
    DockStyle
    -0.53
    ագրություններ
    -0.53
    POSITIVE LOGITS
    <bos>
    0.67
    marginHorizontal
    0.59
    transQ
    0.55
     protoimpl
    0.50
     of
    0.50
     turn
    0.47
     @"/
    0.45
     sp
    0.45
     bit
    0.44
    +
    0.44
    Activations Density 0.002%

    No Known Activations