© 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. 4470
    Prev
    Next
    INDEX
    Explanations

    Various academic topics

    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
    .–
    -0.46
     life
    -0.45
    tamol
    -0.44
     Waray
    -0.43
    life
    -0.42
    .•
    -0.41
    .”.
    -0.40
    <bos>
    -0.40
    selves
    -0.40
     hesitate
    -0.39
    POSITIVE LOGITS
     ProtoMessage
    0.65
    جوايز
    0.65
    {}{}
    0.63
    __*/
    0.62
    ParallelGroup
    0.61
    Enllaces
    0.59
     Periodicals
    0.58
    ContentAlignment
    0.58
     GenerationType
    0.57
    >//
    0.57
    Activations Density 0.017%

    No Known Activations