© 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. 1-CLT-HP
    7. 9172
    Prev
    Next
    INDEX
    Explanations

    mouth

    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
     mouth
    -1.06
     Mouth
    -0.82
     mouths
    -0.78
    Mouth
    -0.71
    XmlAccessType
    -0.68
    mouth
    -0.65
    findpost
    -0.56
     bouche
    -0.52
     estekak
    -0.50
    PageRoute
    -0.49
    POSITIVE LOGITS
    </tfoot>
    0.64
    utilisons
    0.59
    artamentos
    0.59
     Delano
    0.54
    stones
    0.53
    hopped
    0.52
    utete
    0.51
    hedrals
    0.50
    phora
    0.50
    cibly
    0.49
    Activations Density 0.003%

    No Known Activations