© 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. 14338
    Prev
    Next
    INDEX
    Explanations

    within

    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
     ujednoznacz
    -0.75
     tartalomajánló
    -0.68
     vectorielle
    -0.68
    DockStyle
    -0.67
    piram
    -0.65
     Theſe
    -0.63
     مشين
    -0.63
     TextAlign
    -0.62
    intenant
    -0.62
     TimeUnit
    -0.62
    POSITIVE LOGITS
     us
    0.59
    .
    0.51
    Semitic
    0.49
     its
    0.49
     our
    0.49
     his
    0.44
     ears
    0.43
    <bos>
    0.43
     nature
    0.41
     joaat
    0.40
    Activations Density 0.005%

    No Known Activations