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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94725
    Prev
    Next
    INDEX
    Explanations

    each

    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
     of
    -0.80
    ècie
    -0.70
     المعيارى
    -0.65
    ichord
    -0.59
    IVEREF
    -0.57
    ikon
    -0.55
    Autoritní
    -0.55
    </thead>
    -0.54
    uação
    -0.54
    TagMode
    -0.53
    POSITIVE LOGITS
     abstinence
    0.54
     dummies
    0.49
     deletions
    0.47
     registrations
    0.47
    //-->
    0.46
    RemoteException
    0.46
    TagHelpers
    0.45
     absten
    0.45
    UnusedPrivate
    0.45
     Massacre
    0.44
    Activations Density 0.001%

    No Known Activations