© 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. 72940
    Prev
    Next
    INDEX
    Explanations

    scientific/technical descriptions

    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
     bross
    -0.72
    SequentialGroup
    -0.66
    BERGER
    -0.64
    Obrázky
    -0.62
    InvalidProtocol
    -0.59
     GenerationType
    -0.59
     présidenti
    -0.59
    Hozzáférés
    -0.58
    Groovy
    -0.57
    LayoutPanel
    -0.57
    POSITIVE LOGITS
     оригіналу
    0.64
     care
    0.50
    __(/*!
    0.48
     fairly
    0.47
    ➟
    0.44
    ="//
    0.44
    ctically
    0.44
     conserve
    0.42
     plan
    0.42
     equit
    0.42
    Activations Density 0.000%

    No Known Activations