© 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. 5323
    Prev
    Next
    INDEX
    Explanations

    same

    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
     Chwiliwch
    -0.74
    ]),
    -0.74
    <bos>
    -0.73
     AssemblyTitle
    -0.72
     Bioaccumulative
    -0.70
    });*/
    -0.63
    astéro
    -0.63
    KURZBESCHREIBUNG
    -0.63
     can
    -0.62
    Persön
    -0.62
    POSITIVE LOGITS
     appunto
    0.55
     isolato
    0.55
    例文帳に追加
    0.50
     superiori
    0.49
     trattato
    0.47
     potrivit
    0.46
     supérieures
    0.46
     umana
    0.44
     florales
    0.42
     plurality
    0.42
    Activations Density 0.019%

    No Known Activations