© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4068
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
     فريبيس
    -1.09
     houſe
    -0.79
     تانيه
    -0.77
     pleaſure
    -0.77
    AndEndTag
    -0.77
     متعلقه
    -0.76
     myſelf
    -0.76
     leaſt
    -0.75
     iſt
    -0.75
    providedIn
    -0.75
    POSITIVE LOGITS
    ’
    0.57
    '
    0.51
     Spec
    0.50
    gy
    0.49
    opis
    0.48
     ever
    0.48
     '
    0.45
    let
    0.45
     ‘
    0.44
    ?
    0.44
    Activations Density 0.016%

    No Known Activations