© 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. 4553
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
    DebuggerNonUser
    -0.65
    lists
    -0.56
    LISTS
    -0.55
    googleapis
    -0.54
    rå
    -0.54
    ørn
    -0.53
     HasFactory
    -0.53
    Lists
    -0.52
     disponibilités
    -0.50
     Administrativna
    -0.49
    POSITIVE LOGITS
     Hampton
    0.53
    MLLoader
    0.51
     Eggers
    0.50
     disambiguazione
    0.49
    دانشنامهٔ
    0.47
     дописавши
    0.46
    AndEndTag
    0.46
     sharper
    0.46
    runApp
    0.46
     pinulongan
    0.46
    Activations Density 0.005%

    No Known Activations