© 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. 77843
    Prev
    Next
    INDEX
    Explanations

    .

    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
     صوتيه
    -0.69
    adə
    -0.54
    styleType
    -0.50
    ib
    -0.49
    الحياه
    -0.49
    SOUNDBITE
    -0.48
    orElseThrow
    -0.47
    IActionResult
    -0.46
    rechnung
    -0.46
    LabelTagHelper
    -0.45
    POSITIVE LOGITS
    KommentareTeilen
    0.63
     Audiodateien
    0.59
    CodedInputStream
    0.55
     vnd
    0.54
     Woodbury
    0.53
    mopolitan
    0.52
    ✭✭
    0.52
    OGND
    0.51
     myſelf
    0.50
    tonode
    0.50
    Activations Density 0.002%

    No Known Activations