© 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. 92434
    Prev
    Next
    INDEX
    Explanations

    the

    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
     motorist
    -0.43
    undaki
    -0.41
     bilgi
    -0.40
     cuantos
    -0.40
    }}}
    -0.38
    ینت
    -0.38
    keri
    -0.37
     motor
    -0.36
    LATEST
    -0.36
    ciente
    -0.36
    POSITIVE LOGITS
    VersionUID
    0.98
     AssemblyProduct
    0.94
    SharedDtor
    0.91
     MainAxisSize
    0.89
    __(/*!
    0.88
    sidemargin
    0.87
     '\\;'
    0.85
    WriteBarrier
    0.83
     Wicidata
    0.82
     BoxDecoration
    0.82
    Activations Density 0.005%

    No Known Activations