© 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. 1-CLT-HP
    7. 15233
    Prev
    Next
    INDEX
    Explanations

    Code snippets/data

    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
     protoimpl
    -0.71
     ModelExpression
    -0.71
    GEBURTSDATUM
    -0.68
    ThroughAttribute
    -0.67
    AndEndTag
    -0.63
    )');
    -0.62
    Geplaatst
    -0.60
     AssemblyVersion
    -0.60
    $',
    -0.59
     calendriers
    -0.58
    POSITIVE LOGITS
     mine
    0.51
     excepted
    0.50
     Altar
    0.50
     altar
    0.49
     nuns
    0.48
     Szk
    0.48
     Protestants
    0.47
     Bastille
    0.47
     diocese
    0.47
     devotees
    0.47
    Activations Density 0.008%

    No Known Activations