© 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. 5-CLT-HP
    7. 5785
    Prev
    Next
    INDEX
    Explanations

    Locations and rankings

    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
    eradish
    -0.52
     дописавши
    -0.47
    >);
    -0.46
    ".
    -0.44
    },
    -0.42
    ].
    -0.41
    abestanden
    -0.40
    fjspx
    -0.40
    complexContent
    -0.40
    >}
    -0.40
    POSITIVE LOGITS
    تقاوى
    0.62
    NameInMap
    0.61
    maßen
    0.59
    HomeAsUpEnabled
    0.59
     protoimpl
    0.57
     Offisielt
    0.57
     EconPapers
    0.56
    jangkau
    0.56
     autorytatywna
    0.55
     center
    0.54
    Activations Density 0.003%

    No Known Activations