© 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. 92600
    Prev
    Next
    INDEX
    Explanations

    important topics

    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
    hyrchwyd
    -0.71
    WriteBarrier
    -0.68
     préc
    -0.66
     SwitchCompat
    -0.63
     mergeFrom
    -0.63
    archiviato
    -0.62
     frågan
    -0.61
     roulant
    -0.61
     ligiloj
    -0.60
     المعيارى
    -0.60
    POSITIVE LOGITS
     createContext
    0.40
    makeConstraints
    0.40
     experience
    0.39
    protoc
    0.39
     economies
    0.39
     eight
    0.39
    experience
    0.38
    dann
    0.38
    }^{+\
    0.37
    KURZBESCHREIBUNG
    0.37
    Activations Density 0.001%

    No Known Activations