© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75474
    Prev
    Next
    INDEX
    Explanations

    Lich

    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
     otomatig
    -0.63
    énario
    -0.63
    ModelAdmin
    -0.58
    WebElementEntity
    -0.58
     Италијани
    -0.56
    yntaxException
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     виправивши
    -0.52
     odkazy
    -0.50
    bkz
    -0.50
    POSITIVE LOGITS
     doInBackground
    0.59
    PyTuple
    0.55
    ág
    0.54
    styleUrls
    0.54
     Inde
    0.53
     насељу
    0.53
     Diversion
    0.51
    sup
    0.50
    MessageInfo
    0.49
    capes
    0.48
    Activations Density 0.001%

    No Known Activations