© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42090
    Prev
    Next
    INDEX
    Explanations

    objective

    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
    Aims
    -1.07
    Objective
    -0.71
     Aims
    -0.71
    DockStyle
    -0.70
     aims
    -0.69
     AssemblyCulture
    -0.69
    bbene
    -0.68
    참고
    -0.67
    SourceChecksum
    -0.67
    Objectives
    -0.65
    POSITIVE LOGITS
    ness
    0.65
    ifications
    0.50
    nesses
    0.49
    nses
    0.48
     cost
    0.48
     biznes
    0.46
     become
    0.46
     Empresas
    0.45
     multiplication
    0.45
     wa
    0.44
    Activations Density 0.058%

    No Known Activations