© 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. 1-CLT-HP
    7. 15114
    Prev
    Next
    INDEX
    Explanations

    molecule

    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
     molecules
    -0.66
    ForRow
    -0.60
     molecule
    -0.59
     Molecules
    -0.50
    ::<
    -0.49
    HtmlAttribute
    -0.47
     Molecule
    -0.47
     molé
    -0.45
    )}</
    -0.45
    )))));
    -0.45
    POSITIVE LOGITS
    UnknownFieldSet
    0.71
     protoimpl
    0.65
    NameInMap
    0.64
    Abitanti
    0.63
    SpringBootTest
    0.63
    InitVars
    0.63
    ":[{
    0.59
    protoc
    0.58
    Havolalar
    0.57
     Roskov
    0.56
    Activations Density 0.134%

    No Known Activations