© 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. 0-CLT-HP
    7. 95043
    Prev
    Next
    INDEX
    Explanations

    those

    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
     these
    -0.67
    these
    -0.54
    これらの
    -0.54
    These
    -0.52
    setAccessible
    -0.52
     those
    -0.51
    本日は
    -0.50
    rxjs
    -0.50
     a
    -0.49
     (
    -0.49
    POSITIVE LOGITS
     Administrativna
    0.72
     AssemblyTitle
    0.66
     kasarigan
    0.63
    paksa
    0.62
     agencies
    0.60
     سكانية
    0.60
    oa̍t
    0.59
    ROIT
    0.59
    eseorang
    0.58
    Демографія
    0.58
    Activations Density 0.036%

    No Known Activations