© 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. 91841
    Prev
    Next
    INDEX
    Explanations

    actions that modify things

    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
     يتيمه
    -0.79
    bewerken
    -0.75
     tartalomajánló
    -0.73
     المعيارى
    -0.70
     виправивши
    -0.70
     dAtA
    -0.66
     and
    -0.65
    AutoresizingMask
    -0.65
     Efq
    -0.64
    stdc
    -0.63
    POSITIVE LOGITS
     the
    0.74
     a
    0.69
     most
    0.69
     different
    0.66
     an
    0.66
     all
    0.56
     many
    0.55
     some
    0.53
     normal
    0.51
     na
    0.50
    Activations Density 0.001%

    No Known Activations