© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3138
    Prev
    Next
    INDEX
    Explanations

    what

    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
    +#+#
    -0.97
    Enllaços
    -0.90
    StoryboardSegue
    -0.88
     esternos
    -0.85
    IsContent
    -0.84
    NameInMap
    -0.84
    tagHelperRunner
    -0.84
    IntoConstraints
    -0.83
     nakalista
    -0.81
     mxArray
    -0.81
    POSITIVE LOGITS
    妥
    0.48
    いいのか
    0.40
     مناس
    0.40
     sådan
    0.39
     important
    0.37
    通
    0.36
    Unfortunately
    0.36
    </tbody>
    0.36
     potential
    0.35
    停
    0.35
    Activations Density 0.001%

    No Known Activations