© 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. 5283
    Prev
    Next
    INDEX
    Explanations

    people

    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
    verwijspagina
    -0.76
    ètement
    -0.60
    ;';
    -0.56
     estekak
    -0.56
     $:$
    -0.55
    </thead>
    -0.54
    }>;
    -0.52
     Exactos
    -0.51
    öße
    -0.49
    ">:
    -0.48
    POSITIVE LOGITS
     his
    0.89
     him
    0.59
     he
    0.59
    his
    0.58
     himself
    0.58
    monių
    0.56
    getDoctrine
    0.54
    /*
    0.53
    :✨
    0.52
    くると
    0.50
    Activations Density 0.016%

    No Known Activations