© 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. 72604
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    ActionCreators
    -0.49
    ynku
    -0.49
    phas
    -0.47
    setArguments
    -0.45
     Domini
    -0.45
     Dont
    -0.45
    asuring
    -0.45
    icoot
    -0.44
     menus
    -0.44
    BindView
    -0.44
    POSITIVE LOGITS
     Administrativna
    0.62
    UpInside
    0.61
    AndEndTag
    0.60
     ujednoznacz
    0.60
     estekak
    0.60
    OGND
    0.59
     يتيمه
    0.58
     betweenstory
    0.55
    HideFlags
    0.54
     wireType
    0.53
    Activations Density 0.000%

    No Known Activations