© 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. 4820
    Prev
    Next
    INDEX
    Explanations

    Introducing a problem/situation

    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
     كومونز
    -0.65
    findpost
    -0.58
    StoryboardSegue
    -0.56
    AllAfrica
    -0.56
    OGND
    -0.56
    Datuak
    -0.54
     actionMode
    -0.54
    Geografi
    -0.52
     betweenstory
    -0.51
     Bourgoin
    -0.51
    POSITIVE LOGITS
    .
    0.55
    IVEREF
    0.50
     entityManager
    0.50
    ponses
    0.49
    Portály
    0.49
     virkelig
    0.49
    SharedDtor
    0.48
     Always
    0.47
    Gotcha
    0.47
    prepareStatement
    0.46
    Activations Density 0.023%

    No Known Activations