© 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. 92351
    Prev
    Next
    INDEX
    Explanations

    cities/towns

    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
    ActionMode
    -0.57
    ]));
    -0.54
    MeasureSpec
    -0.54
    webElement
    -0.54
    />";
    -0.52
    іга
    -0.51
    igshid
    -0.50
    ")));
    -0.50
    venido
    -0.50
    DeleteCommand
    -0.50
    POSITIVE LOGITS
    verifyException
    0.55
    MatIconModule
    0.49
     centre
    0.48
     life
    0.47
     QName
    0.45
    داية
    0.45
     terminal
    0.43
    sidemargin
    0.43
     Ärzte
    0.43
     muelle
    0.41
    Activations Density 0.003%

    No Known Activations