© 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. 0-CLT-HP
    7. 94202
    Prev
    Next
    INDEX
    Explanations

    diverse text snippets

    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
    abank
    -0.63
    fois
    -0.55
    Slik
    -0.54
    TextUtils
    -0.54
     onStop
    -0.54
     defStyle
    -0.54
     crook
    -0.53
    thodoxy
    -0.53
    льки
    -0.52
    dexter
    -0.51
    POSITIVE LOGITS
    SourceChecksum
    0.69
     estimés
    0.67
    Personendaten
    0.66
    StoryboardSegue
    0.65
    ագրություններ
    0.63
    TestingModule
    0.60
    yntaxException
    0.59
    HtmlAttribute
    0.56
    protoc
    0.56
    UnsafeEnabled
    0.56
    Activations Density 2.171%

    No Known Activations