© 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. 97995
    Prev
    Next
    INDEX
    Explanations

    website or code content

    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
     تضيفلها
    -0.61
    URLException
    -0.60
     насељу
    -0.60
    ագրություններ
    -0.59
    Personendaten
    -0.54
     nahilalakip
    -0.48
    хьтан
    -0.47
    TintMode
    -0.46
    anglès
    -0.46
     gynhyrchwyd
    -0.46
    POSITIVE LOGITS
     AssemblyTitle
    0.78
    enderror
    0.71
    >>()
    0.69
     depositphotos
    0.65
     ∼
    0.64
    ^(@)
    0.64
     $>$
    0.63
     Eſ
    0.61
     GeV
    0.60
     ẞ
    0.60
    Activations Density 0.000%

    No Known Activations