© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93171
    Prev
    Next
    INDEX
    Explanations

    for

    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
     Numerade
    -0.65
    ."));
    -0.63
    ]")
    -0.63
    ."),
    -0.62
    ]='\
    -0.61
    .)}
    -0.60
     firebaseConfig
    -0.60
    ]");
    -0.60
    ."</
    -0.60
    expandindo
    -0.59
    POSITIVE LOGITS
     of
    0.64
    hö
    0.57
    unesse
    0.53
    Predecesor
    0.51
    unte
    0.51
    kloped
    0.51
     hon
    0.51
     on
    0.50
    orteur
    0.50
    ophys
    0.49
    Activations Density 0.000%

    No Known Activations