© 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. 92604
    Prev
    Next
    INDEX
    Explanations

    editions and versions

    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
    gnore
    -0.68
     disambiguazione
    -0.66
    tonode
    -0.65
    OGND
    -0.62
    TimerTask
    -0.59
    rungsseite
    -0.58
    makeConstraints
    -0.57
     Projektu
    -0.57
    ---*/
    -0.54
    ="@+
    -0.54
    POSITIVE LOGITS
     pouvaient
    0.52
    fillType
    0.47
     apresentação
    0.46
     semblent
    0.45
    bbero
    0.45
     istnieje
    0.44
     chré
    0.44
    Link
    0.44
    offerta
    0.43
     précédentes
    0.43
    Activations Density 0.150%

    No Known Activations