© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90775
    Prev
    Next
    INDEX
    Explanations

    plan

    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
    Personensuche
    -0.86
     GoogleFonts
    -0.77
    Sklici
    -0.73
    OGND
    -0.72
    IsContent
    -0.71
     "..\..\
    -0.71
    WithMany
    -0.69
    VersionUID
    -0.69
     dieux
    -0.68
    AnchorStyles
    -0.67
    POSITIVE LOGITS
     of
    0.61
    >-->
    0.51
    '>";
    0.48
    ()]);
    0.46
     underway
    0.44
    >');
    0.43
     stanovnika
    0.43
     sleeved
    0.42
    ."));
    0.42
    rych
    0.42
    Activations Density 0.019%

    No Known Activations