© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77491
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/blogs

    np_max-act-logits · 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
    GHIJKLM
    -0.68
    Hentet
    -0.64
    KommentareTeilen
    -0.61
     contextLoads
    -0.60
     snippetHide
    -0.58
     وتسجيلات
    -0.57
    ]")]
    -0.57
     STATION
    -0.56
    Datuak
    -0.55
     ujednoznacz
    -0.55
    POSITIVE LOGITS
    DataContract
    0.45
     velkommen
    0.44
     mc
    0.44
    Home
    0.44
     Home
    0.43
    ++){
    0.43
    setArguments
    0.43
    home
    0.42
     assuring
    0.42
    tomos
    0.41
    Activations Density 0.000%

    No Known Activations