© 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. 97962
    Prev
    Next
    INDEX
    Explanations

    is/are

    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
    SOUNDBITE
    -0.63
    Hochspringen
    -0.55
    componentWill
    -0.54
    OGND
    -0.52
     noDo
    -0.49
     noten
    -0.49
    styleable
    -0.48
    GenerationType
    -0.47
     initComponents
    -0.46
    日閲覧
    -0.45
    POSITIVE LOGITS
     the
    0.63
    TestBed
    0.61
    BitConverter
    0.56
    uría
    0.52
    version
    0.50
     Administrativna
    0.50
     ++;
    0.44
    utare
    0.44
    its
    0.44
    NonQuery
    0.43
    Activations Density 0.008%

    No Known Activations