© 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. 20-CLT-HP
    7. 76783
    Prev
    Next
    INDEX
    Explanations

    Mer

    np_max-act-logits · 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
    
    -0.69
    سطس
    -0.66
    SBATCH
    -0.65
    PMailer
    -0.63
    actionMode
    -0.61
    LEncoder
    -0.60
    сшта
    -0.59
    jspb
    -0.57
    antaine
    -0.57
    PasswordEncoder
    -0.56
    POSITIVE LOGITS
    thy
    0.52
    fjspx
    0.47
    borne
    0.45
    bion
    0.44
    rift
    0.44
    estia
    0.44
     BorderRadius
    0.43
    ione
    0.43
    rist
    0.42
    rif
    0.42
    Activations Density 0.001%

    No Known Activations