© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    scientific observations

    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
    observed
    -0.59
     observed
    -0.59
     discovered
    -0.57
    }";
    -0.53
    #
    -0.48
    }");
    -0.48
    });*/
    -0.47
     وتسجيلات
    -0.46
     noticed
    -0.46
    discovered
    -0.46
    POSITIVE LOGITS
    complexContent
    0.92
    الحياه
    0.68
    eachtet
    0.65
    __(/*!
    0.63
    WriteBarrier
    0.62
    ActionCreators
    0.60
     tight
    0.60
    Datuak
    0.59
     luy
    0.58
    IGENCE
    0.56
    Activations Density 0.022%

    No Known Activations