© 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. 15244
    Prev
    Next
    INDEX
    Explanations

    time periods/ages

    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
     Exacts
    -0.50
     knji
    -0.50
    ']],
    -0.49
    arean
    -0.49
    imageshack
    -0.47
    ########.
    -0.46
    )['
    -0.46
     jazdy
    -0.45
    ‴
    -0.44
    Personendaten
    -0.43
    POSITIVE LOGITS
    providedIn
    0.73
     <<<<<<<<<<<<<<
    0.67
    ftagPool
    0.65
    WebControls
    0.64
    ioutil
    0.63
    хіво
    0.61
     createState
    0.58
     /\.
    0.56
    ToOne
    0.56
    și
    0.55
    Activations Density 0.047%

    No Known Activations