© 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. 97093
    Prev
    Next
    INDEX
    Explanations

    round

    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
     saites
    -0.56
     OFDb
    -0.54
    !!,
    -0.50
     المعيارى
    -0.49
     виправивши
    -0.48
    IntoConstraints
    -0.45
     !!
    -0.45
     !!!!
    -0.44
    !!!!!
    -0.44
     Folio
    -0.44
    POSITIVE LOGITS
    <bos>
    0.67
     consultato
    0.58
    anek
    0.53
    WithMany
    0.52
    thylamine
    0.51
    contentLoaded
    0.50
    착
    0.50
    webElementGuid
    0.50
     Tiempo
    0.50
    ÈS
    0.50
    Activations Density 0.000%

    No Known Activations