© 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. 5-CLT-HP
    7. 4557
    Prev
    Next
    INDEX
    Explanations

    ago

    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
    LookAnd
    -0.63
    sizeCache
    -0.59
     mergeFrom
    -0.54
     otomatig
    -0.53
    SharedCtor
    -0.52
    webElementXpaths
    -0.52
    Autoritní
    -0.52
    Filler
    -0.51
    Personensuche
    -0.51
     run
    -0.51
    POSITIVE LOGITS
     with
    0.76
     when
    0.63
    Източници
    0.54
    AndEndTag
    0.54
    存于互联网档案馆
    0.50
    acquisto
    0.49
     devoting
    0.48
     preparing
    0.48
    — 
    0.47
     among
    0.46
    Activations Density 0.001%

    No Known Activations