© 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. 0-CLT-HP
    7. 43135
    Prev
    Next
    INDEX
    Explanations

    fiscal

    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
     him
    -1.45
    him
    -0.98
     honom
    -0.86
     Him
    -0.84
     ihm
    -0.73
    Him
    -0.71
     ihn
    -0.69
     lui
    -0.68
    relevant
    -0.66
     relevant
    -0.65
    POSITIVE LOGITS
     Shakspeare
    0.66
     Avic
    0.63
     Phry
    0.57
     Houſe
    0.55
    Description
    0.54
    che
    0.54
    StoryboardSegue
    0.53
    CodeAttribute
    0.53
     Anſ
    0.53
     doubtnut
    0.53
    Activations Density 0.135%

    No Known Activations