© 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. 5-CLT-HP
    7. 91962
    Prev
    Next
    INDEX
    Explanations

    monomer

    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
    󠁢
    -0.71
     quelcon
    -0.70
    GEBURTS
    -0.70
     científicas
    -0.68
    AndEndTag
    -0.68
    WriteTagHelper
    -0.68
    Personensuche
    -0.65
    TestingModule
    -0.64
     ricette
    -0.64
     femininas
    -0.61
    POSITIVE LOGITS
     is
    0.77
     has
    0.65
     may
    0.63
     can
    0.62
     will
    0.58
     are
    0.57
     begin
    0.57
     do
    0.56
     starts
    0.54
     have
    0.54
    Activations Density 0.064%

    No Known Activations