© 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. 91645
    Prev
    Next
    INDEX
    Explanations

    risk

    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
     GenerationType
    -0.61
     of
    -0.61
    Referencies
    -0.58
    Aiheesta
    -0.55
    URLException
    -0.54
     cref
    -0.54
    Portale
    -0.53
     OFDb
    -0.50
    WillAppear
    -0.49
    InstanceState
    -0.48
    POSITIVE LOGITS
     to
    0.67
    UnsafeEnabled
    0.54
    bibitem
    0.52
    jelder
    0.51
     særlig
    0.51
     multiplier
    0.50
    voerd
    0.49
    Aktualisiert
    0.49
     []).
    0.48
     factor
    0.48
    Activations Density 0.001%

    No Known Activations