© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75752
    Prev
    Next
    INDEX
    Explanations

    Foreign language / code

    np_max-act-logits · 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
     autorytatywna
    -0.76
    Controllo
    -0.63
    copg
    -0.59
     correctes
    -0.56
    Fns
    -0.55
    PreInfinity
    -0.55
     resourceCulture
    -0.54
     Réponses
    -0.53
     negatives
    -0.52
    ępu
    -0.52
    POSITIVE LOGITS
     varandra
    0.52
    setVerticalGroup
    0.49
    pædia
    0.49
    ]));
    0.49
    Filmografie
    0.48
    كويكب
    0.44
     souhaitez
    0.44
     tiroirs
    0.43
     layui
    0.42
     boî
    0.42
    Activations Density 0.000%

    No Known Activations