© 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. 93128
    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
    IContainer
    -0.69
    setVerticalGroup
    -0.63
     snippetHide
    -0.59
    PRNewswire
    -0.57
    COUVER
    -0.56
    ContentLoaded
    -0.55
    phosa
    -0.55
     autorytatywna
    -0.55
    labelledby
    -0.53
    encodeWith
    -0.53
    POSITIVE LOGITS
    ]$}
    0.56
    matchCondition
    0.49
     Case
    0.49
    ]--;
    0.47
    =?";
    0.46
    FlatList
    0.46
    ächs
    0.45
     Environ
    0.44
    Aholisi
    0.44
     createContext
    0.43
    Activations Density 0.002%

    No Known Activations