© 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. 5-CLT-HP
    7. 3546
    Prev
    Next
    INDEX
    Explanations

    structured

    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
    GOTREF
    -0.57
    assertAll
    -0.54
    enberg
    -0.47
    bestos
    -0.47
     Arrondissement
    -0.46
    nan
    -0.45
    asanjo
    -0.45
    ISPR
    -0.44
     consecu
    -0.44
    事了
    -0.44
    POSITIVE LOGITS
    IndentedString
    0.67
     snippetHide
    0.61
    MockBean
    0.57
     judges
    0.57
     visitor
    0.56
     justices
    0.56
     visitors
    0.56
     referee
    0.56
     sumpay
    0.53
     electors
    0.51
    Activations Density 0.004%

    No Known Activations