© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5246
    Prev
    Next
    INDEX
    Explanations

    Technical or procedural text

    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
     nakalista
    -0.94
     estekak
    -0.84
    ThroughAttribute
    -0.81
     resourceCulture
    -0.73
    Hochspringen
    -0.68
    GEBURTSDATUM
    -0.67
     GenerationType
    -0.67
    HomeAsUpEnabled
    -0.65
     a
    -0.64
    ViewFeatures
    -0.64
    POSITIVE LOGITS
     syndrome
    0.50
     malady
    0.46
     phenomenon
    0.44
    ?’
    0.43
    جانب
    0.43
     anyhow
    0.43
    ?“
    0.42
    ’?
    0.42
    IAB
    0.42
     Ślą
    0.41
    Activations Density 0.005%

    No Known Activations