© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96173
    Prev
    Next
    INDEX
    Explanations

    of

    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
     typelib
    -0.57
    Stand
    -0.51
    RegressionTest
    -0.51
    BeginContext
    -0.49
     cabbage
    -0.47
    Diweddarwch
    -0.46
     stand
    -0.45
    nisk
    -0.45
    azy
    -0.44
     fier
    -0.44
    POSITIVE LOGITS
    verwijspagina
    0.59
    Olvid
    0.58
    balleur
    0.56
    IndentedString
    0.55
     للمعارف
    0.54
     gainera
    0.53
    caux
    0.51
     ordini
    0.51
    ership
    0.50
    enging
    0.50
    Activations Density 0.001%

    No Known Activations