© 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. 20-CLT-HP
    7. 76429
    Prev
    Next
    INDEX
    Explanations

    technical/obscure vocabulary

    np_max-act-logits · 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
    berdayakan
    -0.46
     Hügel
    -0.45
     alley
    -0.43
     voeten
    -0.43
     Micho
    -0.42
    куль
    -0.42
    MethodImpl
    -0.41
    ņem
    -0.41
    reet
    -0.40
     hill
    -0.40
    POSITIVE LOGITS
     Wikimédia
    0.65
     Chwiliwch
    0.60
    WireFormatLite
    0.60
    __":
    0.54
    StandardCharsets
    0.54
     lagu
    0.52
    XmlAccessType
    0.52
    lorum
    0.52
    WindowConstants
    0.52
    ArgsConstructor
    0.49
    Activations Density 0.004%

    No Known Activations