© 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. 0-CLT-HP
    7. 94985
    Prev
    Next
    INDEX
    Explanations

    positive attributes

    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
    NameInMap
    -0.75
    Kjelder
    -0.63
     disponibilités
    -0.58
    amente
    -0.57
     nakalista
    -0.57
     kasarigan
    -0.54
    posedge
    -0.53
    jspx
    -0.52
    });
    -0.50
    TagMode
    -0.49
    POSITIVE LOGITS
    toplankton
    0.59
    toma
    0.58
     OkHttpClient
    0.57
    RestTemplate
    0.57
     geology
    0.56
     Sime
    0.54
    AndUpdate
    0.54
     Egal
    0.54
     biology
    0.53
     Spinoza
    0.53
    Activations Density 0.121%

    No Known Activations