© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14196
    Prev
    Next
    INDEX
    Explanations

    Ha/Hai/Haq

    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
     Ha
    -1.12
    Ha
    -1.06
     ha
    -0.78
     HA
    -0.61
    CrossRef
    -0.60
    intios
    -0.58
    HA
    -0.56
    ha
    -0.56
    opolis
    -0.52
    }{*}{}
    -0.52
    POSITIVE LOGITS
    AnchorStyles
    0.66
    DockStyle
    0.65
    UnusedPrivate
    0.60
    XmlAccessorType
    0.54
    GEBURTSDATUM
    0.54
     AppCompatTheme
    0.54
    es
    0.53
     tendenza
    0.52
    ArrowToggle
    0.51
    BeginContext
    0.51
    Activations Density 0.014%

    No Known Activations