© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92440
    Prev
    Next
    INDEX
    Explanations

    open curly bracket

    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
    tagHelper
    -0.53
    %)$
    -0.52
    )))));
    -0.52
    }$​
    -0.49
     esternos
    -0.49
     rhestr
    -0.46
     ModelExpression
    -0.46
    kamers
    -0.46
    GEBURTSDATUM
    -0.46
    ⓧ
    -0.46
    POSITIVE LOGITS
     fermo
    0.61
    raborty
    0.56
    fromnode
    0.55
    ProgressHUD
    0.53
     prosent
    0.53
    Ered
    0.52
    rhosis
    0.52
    Destinations
    0.52
     ControllerBase
    0.52
    ঙ
    0.51
    Activations Density 0.130%

    No Known Activations