© 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. 5207
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

    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
     referenties
    -0.77
    CloseOperation
    -0.77
     propOrder
    -0.71
    MigrationBuilder
    -0.69
     متعلقه
    -0.66
     nahilalakip
    -0.65
     vastaan
    -0.63
     AssemblyCulture
    -0.63
    EDEFAULT
    -0.59
     necessarily
    -0.58
    POSITIVE LOGITS
     I
    0.75
     he
    0.61
    Datuak
    0.52
     February
    0.51
    asiun
    0.51
     winter
    0.50
     summer
    0.49
     Memorial
    0.48
     January
    0.47
     she
    0.47
    Activations Density 0.000%

    No Known Activations