© 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. 92995
    Prev
    Next
    INDEX
    Explanations

    gets

    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
     мәкал
    -0.50
     diken
    -0.47
     abbiamo
    -0.46
    khó
    -0.46
    front
    -0.45
    κτηρισ
    -0.45
     ơn
    -0.45
    AddTagHelper
    -0.44
    long
    -0.44
    contentLoaded
    -0.44
    POSITIVE LOGITS
     older
    0.82
    RegressionTest
    0.75
    ]?.
    0.63
    .
    0.63
     BrowserModule
    0.62
    ]]
    0.61
    gående
    0.60
     adequate
    0.59
     used
    0.58
     too
    0.58
    Activations Density 0.000%

    No Known Activations