© 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. 4-CLT-HP
    7. 547
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Hentet
    -0.48
    archiviato
    -0.44
    <()>
    -0.44
    olische
    -0.44
    خصة
    -0.43
     demikian
    -0.43
    resar
    -0.42
     Seeder
    -0.42
    piram
    -0.41
     अपना
    -0.40
    POSITIVE LOGITS
     AssemblyTitle
    0.65
     speak
    0.65
     speaks
    0.63
    Speak
    0.60
     speakers
    0.58
     препратки
    0.58
     Administrativna
    0.57
    ,
    0.57
    ftagPool
    0.57
     Speak
    0.56
    Activations Density 0.004%

    No Known Activations