© 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. 1-CLT-HP
    7. 45922
    Prev
    Next
    INDEX
    Explanations

    multiple languages/contexts

    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
    addGap
    -0.48
    <bos>
    -0.46
    tonode
    -0.45
    værende
    -0.44
    HostException
    -0.43
     vastaan
    -0.43
    TestingModule
    -0.41
     fleste
    -0.40
    zeria
    -0.40
    ihnachten
    -0.39
    POSITIVE LOGITS
     Kae
    0.65
     PKK
    0.59
     K
    0.57
     Klan
    0.57
     Tea
    0.56
     Aun
    0.54
     Pit
    0.53
     Ko
    0.53
     Bryn
    0.53
     Kr
    0.52
    Activations Density 0.023%

    No Known Activations