© 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. 73471
    Prev
    Next
    INDEX
    Explanations

    technical/legal documents

    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
    #+#
    -0.64
    ništvo
    -0.63
     beginnetje
    -0.59
    Демографія
    -0.59
    AddTagHelper
    -0.59
     Pointer
    -0.59
    thâu
    -0.58
    AndEndTag
    -0.55
    ItemBackground
    -0.55
    IActionResult
    -0.54
    POSITIVE LOGITS
     ste
    0.59
    Bone
    0.52
    তথ্যসূত্র
    0.50
     Ste
    0.50
     bone
    0.50
    bustible
    0.49
    tal
    0.49
     tal
    0.49
    GetChild
    0.46
    BONE
    0.46
    Activations Density 0.000%

    No Known Activations