© 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. 4901
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    <eos>
    -0.40
     ettei
    -0.40
    ↵
    -0.39
     obicei
    -0.38
     není
    -0.36
    ことなく
    -0.36
     länder
    -0.36
    fuhr
    -0.35
     politiche
    -0.35
    ɫ
    -0.35
    POSITIVE LOGITS
    DoubleQuotes
    0.99
     nakalista
    0.97
    RenderAtEndOf
    0.96
     متعلقه
    0.96
    ConstraintMaker
    0.82
    URLException
    0.81
    ArgsConstructor
    0.79
    SharedDtor
    0.79
    astify
    0.77
     Италијани
    0.77
    Activations Density 0.014%

    No Known Activations