© 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. 1-CLT-HP
    7. 14505
    Prev
    Next
    INDEX
    Explanations

    establish

    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
     незавершена
    -0.52
    })));
    -0.49
     betweenstory
    -0.48
    ตัวเอง
    -0.46
    robial
    -0.44
    Vidite
    -0.43
    URLException
    -0.42
    ramanian
    -0.40
     fortemente
    -0.40
    homonymie
    -0.40
    POSITIVE LOGITS
    makeConstraints
    0.68
    DebuggerStep
    0.63
     ISNI
    0.61
     متعلقه
    0.60
     /\.
    0.59
     trash
    0.58
    GeneratedValue
    0.58
     DbType
    0.58
    yska
    0.57
     actionTypes
    0.57
    Activations Density 0.021%

    No Known Activations